Public scan — anyone with this URL can view this analysis. Sign up to track your own repos privately, run scheduled re-scans, and get AI fix prompts via your dashboard.

UKGovernmentBEIS/inspect_evals

https://github.com/UKGovernmentBEIS/inspect_evals · scanned 2026-06-16 22:23 UTC (1 month, 2 weeks ago)

1275 raw signals (0 security + 1275 graph)

File as issue Image

UNIFIED Repobility · multi-layer engine · AI coders

Complete repo analysis

Last scanned 1 month, 2 weeks ago · v3 · 543 actionable findings from 1 signal source. 100 repeated signals grouped for readability. Security checks, system graph analysis, and verified AI-agent feedback are merged into one review queue.

JSON

100.0% cov · 543 findings

Severity distribution — click a segment to filter

Active filters: excluding tests × Reset all

Severity: Critical 12 High 187 Medium 171 Low 138 9-Layer: Software Security Quality Integrity Frontend Hardware Data Network Cicd Source: Security checks 0 System graph 543 Crowd 0 Layer: Software 17 Frontend 4 Network 9 Hardware 141 Security 213 Cicd 1 Quality 119 Api 39

Exclude dismissed / FP Exclude test files

All 16011 nodes from the latest scan, grouped by kind. Each node is a unit the engine identified (file, function, endpoint, table…). Most users won't need this view — it's primarily for debugging the engine's graph extraction or for AI agents that want to enumerate the project structure.

Label	Layer	Status	Path
`_fake_run`	software	healthy	`tests/test_dep_bump_impact.py:32`
`test_invokes_uv_tree_with_all_groups`	software	healthy	`tests/test_dep_bump_impact.py:37`
`test_detects_dev_group_for_types_pyyaml`	software	healthy	`tests/test_dep_bump_impact.py:48`
`test_types_pyyaml_reported_as_dev_tooling_not_no_impact`	software	healthy	`tests/test_dep_bump_impact.py:66`
`test_epoch_metadata_reduction_issue`	software	healthy	`tests/test_epoch_compatibility.py:47`
`value_based_mean`	software	healthy	`tests/test_epoch_compatibility.py:56`
`calc`	software	healthy	`tests/test_epoch_compatibility.py:71`
`metadata_based_mean`	software	healthy	`tests/test_epoch_compatibility.py:68`
`varying_scorer`	software	healthy	`tests/test_epoch_compatibility.py:85`
`score`	software	healthy	`tests/test_epoch_compatibility.py:86`
`_hf_telemetry_enabled`	software	healthy	`tests/conftest.py:46`
`pytest_addoption`	software	healthy	`tests/conftest.py:54`
`pytest_configure`	software	healthy	`tests/conftest.py:85`
`pytest_collection_modifyitems`	software	healthy	`tests/conftest.py:116`
`pytest_runtest_setup`	software	healthy	`tests/conftest.py:182`
`pytest_runtest_teardown`	software	healthy	`tests/conftest.py:188`
`set_model_roles`	software	healthy	`tests/conftest.py:195`
`pytest_runtest_makereport`	software	healthy	`tests/conftest.py:208`
`pytest_sessionfinish`	software	healthy	`tests/conftest.py:229`
`test_dry_run_does_not_delete`	software	healthy	`tests/test_clean.py:8`
`test_delete_file_and_dir`	software	healthy	`tests/test_clean.py:21`
`test_delete_path_if_exists_raises_for_missing_path`	software	healthy	`tests/test_clean.py:34`
`test_rm_from_dir`	software	healthy	`tests/test_clean.py:43`
`test_rm_from_dir_no_dir`	software	healthy	`tests/test_clean.py:59`
`test_rm_from_dir_empty_dir`	software	healthy	`tests/test_clean.py:65`
`test_registry_imports`	software	healthy	`tests/test_registry_imports.py:7`
`test_registry_exposes_every_eval_yaml_task`	software	healthy	`tests/test_registry_imports.py:12`
`test_direct_eval_call`	software	healthy	`tests/test_autolint_checks.py:20`
`test_module_eval_call`	software	healthy	`tests/test_autolint_checks.py:26`
`test_no_eval_call`	software	healthy	`tests/test_autolint_checks.py:32`
`test_eval_in_function`	software	healthy	`tests/test_autolint_checks.py:38`
`test_different_eval_not_detected`	software	healthy	`tests/test_autolint_checks.py:48`
`test_simple_package`	software	healthy	`tests/test_autolint_checks.py:58`
`test_package_with_version`	software	healthy	`tests/test_autolint_checks.py:62`
`test_package_with_extras`	software	healthy	`tests/test_autolint_checks.py:68`
`test_package_with_environment_marker`	software	healthy	`tests/test_autolint_checks.py:72`
`test_package_with_trailing_space`	software	healthy	`tests/test_autolint_checks.py:76`
`test_empty_string`	software	healthy	`tests/test_autolint_checks.py:80`
`test_complex_specifier`	software	healthy	`tests/test_autolint_checks.py:84`
`test_returns_frozenset`	software	healthy	`tests/test_autolint_checks.py:92`
`test_contains_common_modules`	software	healthy	`tests/test_autolint_checks.py:97`
`test_contains_typing_extensions`	software	healthy	`tests/test_autolint_checks.py:107`
`test_does_not_contain_third_party`	software	healthy	`tests/test_autolint_checks.py:112`
`test_simple_import`	software	healthy	`tests/test_autolint_checks.py:123`
`test_from_import`	software	healthy	`tests/test_autolint_checks.py:131`
`test_nested_import`	software	healthy	`tests/test_autolint_checks.py:139`
`test_multiple_imports`	software	healthy	`tests/test_autolint_checks.py:147`
`test_aliased_import`	software	healthy	`tests/test_autolint_checks.py:163`
`test_finds_task_function`	software	healthy	`tests/test_autolint_checks.py:176`
`test_finds_multiple_task_functions`	software	healthy	`tests/test_autolint_checks.py:189`

Showing first 50 of this kind. Full payload available via the JSON button at the top of the page.

Label	Layer	Status	Path
`TASK_VERSIONING.md`	software	healthy	`TASK_VERSIONING.md`
`CLAUDE.md`	software	healthy	`CLAUDE.md`
`AGENTS.md`	software	healthy	`AGENTS.md`
`ASSETS.yaml`	software	healthy	`ASSETS.yaml`
`MAINTAINERS.md`	software	healthy	`MAINTAINERS.md`
`CONTRIBUTING.md`	software	healthy	`CONTRIBUTING.md`
`CHANGELOG.md`	software	healthy	`CHANGELOG.md`
`AUTOMATED_CHECKS.md`	software	healthy	`AUTOMATED_CHECKS.md`
`.markdownlint.yaml`	software	healthy	`.markdownlint.yaml`
`README.md`	software	healthy	`README.md`
`pyproject.toml`	software	healthy	`pyproject.toml`
`Makefile`	software	healthy	`Makefile`
`LICENSE`	software	healthy	`LICENSE`
`NOTICE`	software	healthy	`NOTICE`
`.pre-commit-config.yaml`	software	healthy	`.pre-commit-config.yaml`
`PACKAGE_VERSIONING.md`	software	healthy	`PACKAGE_VERSIONING.md`
`EVALUATION_CHECKLIST.md`	software	healthy	`EVALUATION_CHECKLIST.md`
`BEST_PRACTICES.md`	software	healthy	`BEST_PRACTICES.md`
`EVAL_REGISTER.md`	software	healthy	`EVAL_REGISTER.md`
`pyproject.toml`	software	healthy	`packages/kernelbench/pyproject.toml`
`pyproject.toml`	software	healthy	`packages/cve_bench/pyproject.toml`
`pyproject.toml`	software	healthy	`packages/bold/pyproject.toml`
`pyproject.toml`	software	healthy	`packages/livebench/pyproject.toml`
`pyproject.toml`	software	healthy	`packages/mle_bench/pyproject.toml`
`pyproject.toml`	software	healthy	`packages/novelty_bench/pyproject.toml`
`pyproject.toml`	software	healthy	`packages/abstention_bench/pyproject.toml`
`test_dep_bump_impact.py`	software	healthy	`tests/test_dep_bump_impact.py`
`test_epoch_compatibility.py`	software	healthy	`tests/test_epoch_compatibility.py`
`conftest.py`	software	healthy	`tests/conftest.py`
`test_clean.py`	software	healthy	`tests/test_clean.py`
`test_registry_imports.py`	software	healthy	`tests/test_registry_imports.py`
`__init__.py`	software	healthy	`tests/__init__.py`
`test_autolint_checks.py`	software	healthy	`tests/test_autolint_checks.py`
`README.md`	software	healthy	`tests/README.md`
`test_generate_readmes.py`	software	healthy	`tests/test_generate_readmes.py`
`test_datasets_hf.py`	software	healthy	`tests/test_datasets_hf.py`
`test_xdist_grouping.py`	software	healthy	`tests/test_xdist_grouping.py`
`test_eval_imports.py`	software	healthy	`tests/test_eval_imports.py`
`test_utils.py`	software	healthy	`tests/test_utils.py`
`test_autolint_best_practices.py`	software	healthy	`tests/test_autolint_best_practices.py`
`test_check_posix_code.py`	software	healthy	`tests/test_check_posix_code.py`
`test_metadata.py`	software	healthy	`tests/test_metadata.py`
`test_prerender_links.py`	software	healthy	`tests/test_prerender_links.py`
`test_asset_tools.py`	software	healthy	`tests/test_asset_tools.py`
`docker_build_trace.py`	software	healthy	`tests/docker_build_trace.py`
`test_add_readme_section.py`	software	healthy	`tests/test_add_readme_section.py`
`test_uccb.py`	software	healthy	`tests/test_uccb/test_uccb.py`
`__init__.py`	software	healthy	`tests/test_uccb/__init__.py`
`__init__.py`	software	healthy	`tests/sevenllm/__init__.py`
`test_sevenllm.py`	software	healthy	`tests/sevenllm/test_sevenllm.py`

Showing first 50 of this kind. Full payload available via the JSON button at the top of the page.

Label	Layer	Status	Path
`TestFindInstallTreeConsumers`	software	healthy	`tests/test_dep_bump_impact.py:36`
`TestRenderHuman`	software	healthy	`tests/test_dep_bump_impact.py:65`
`TestHasEvalCall`	software	healthy	`tests/test_autolint_checks.py:17`
`TestExtractPackageName`	software	healthy	`tests/test_autolint_checks.py:55`
`TestGetStdlibModules`	software	healthy	`tests/test_autolint_checks.py:89`
`TestGetImportsFromFile`	software	healthy	`tests/test_autolint_checks.py:120`
`TestFindTaskFunctions`	software	healthy	`tests/test_autolint_checks.py:173`
`TestGetExportedNames`	software	healthy	`tests/test_autolint_checks.py:247`
`TestBuildParametersSection`	software	healthy	`tests/test_generate_readmes.py:67`
`TestReadmeExists`	software	healthy	`tests/test_generate_readmes.py:216`
`TestGenerateBasicReadme`	software	healthy	`tests/test_generate_readmes.py:233`
`TestFormatParameter`	software	healthy	`tests/test_generate_readmes.py:286`
`TestParseDocstringParameters`	software	healthy	`tests/test_generate_readmes.py:442`
`TestFormatTypeAnnotation`	software	healthy	`tests/test_generate_readmes.py:650`
`CustomClass`	software	healthy	`tests/test_generate_readmes.py:696`
`TestCleanDefaultValue`	software	healthy	`tests/test_generate_readmes.py:739`
`TestBuildEvaluationReportSection`	software	healthy	`tests/test_generate_readmes.py:858`
`HfDatasetCall`	software	healthy	`tests/test_datasets_hf.py:72`
`TestXdistApplyCollectionGroups`	software	healthy	`tests/test_xdist_grouping.py:27`
`TestCreateStableId`	software	healthy	`tests/test_utils.py:8`
`TestFilterDuplicateIds`	software	healthy	`tests/test_utils.py:134`
`TestGetDecoratorName`	software	healthy	`tests/test_autolint_best_practices.py:15`
`TestGetCallName`	software	healthy	`tests/test_autolint_best_practices.py:61`
`TestGetModelVisitor`	software	healthy	`tests/test_autolint_best_practices.py:107`
`TestSampleIdVisitor`	software	healthy	`tests/test_autolint_best_practices.py:201`
`TestTaskParameterVisitor`	software	healthy	`tests/test_autolint_best_practices.py:275`
`TestTaskDefaultsVisitor`	software	healthy	`tests/test_autolint_best_practices.py:340`
`TestPosixCodeChecker`	software	healthy	`tests/test_check_posix_code.py:9`
`TestCheckFile`	software	healthy	`tests/test_check_posix_code.py:139`
`TestMain`	software	healthy	`tests/test_check_posix_code.py:175`
`TestNormalizeUrl`	software	healthy	`tests/test_asset_tools.py:16`
`TestIsIgnorableUrl`	software	healthy	`tests/test_asset_tools.py:35`
`TestUrlMatchesDeclared`	software	healthy	`tests/test_asset_tools.py:73`
`TestGenerateAssetManifest`	software	healthy	`tests/test_asset_tools.py:140`
`PopenWrapper`	software	healthy	`tests/docker_build_trace.py:199`
`TestNormalizeKey`	software	healthy	`tests/test_add_readme_section.py:16`
`TestHasSectionTags`	software	healthy	`tests/test_add_readme_section.py:41`
`TestFindInsertionPoint`	software	healthy	`tests/test_add_readme_section.py:83`
`TestAddSectionTags`	software	healthy	`tests/test_add_readme_section.py:228`
`TestIntegrationScenarios`	software	healthy	`tests/test_add_readme_section.py:364`
`MockOutput`	software	healthy	`tests/sevenllm/test_sevenllm.py:21`
`DummyMemoryDataset`	software	healthy	`tests/instrumentaleval/test_process_data.py:12`
`SampleModel`	software	healthy	`tests/agentdojo/test_utils.py:10`
`TravelEnvironmentFactory`	software	healthy	`tests/agentdojo/test_deepdiff_wrappers.py:21`
`WorkspaceEnvironmentFactory`	software	healthy	`tests/agentdojo/test_deepdiff_wrappers.py:25`
`TestTokenFuncs`	software	healthy	`tests/niah/test_niah.py:45`
`TestGenerateContextLengths`	software	healthy	`tests/niah/test_niah.py:76`
`TestSampleGenerationFunctions`	software	healthy	`tests/niah/test_niah.py:134`
`TestSampleNeedles`	software	healthy	`tests/niah/test_niah.py:272`
`TestStretchOrSquashNeedles`	software	healthy	`tests/niah/test_niah.py:349`

Showing first 50 of this kind. Full payload available via the JSON button at the top of the page.

Label	Layer	Status	Path
`packages`	software	healthy	`packages`
`kernelbench`	software	healthy	`packages/kernelbench`
`cve_bench`	software	healthy	`packages/cve_bench`
`bold`	software	healthy	`packages/bold`
`livebench`	software	healthy	`packages/livebench`
`mle_bench`	software	healthy	`packages/mle_bench`
`novelty_bench`	software	healthy	`packages/novelty_bench`
`abstention_bench`	software	healthy	`packages/abstention_bench`
`tests`	software	healthy	`tests`
`test_uccb`	software	healthy	`tests/test_uccb`
`sevenllm`	software	healthy	`tests/sevenllm`
`docvqa`	software	healthy	`tests/docvqa`
`instrumentaleval`	software	healthy	`tests/instrumentaleval`
`agentdojo`	software	healthy	`tests/agentdojo`
`niah`	software	healthy	`tests/niah`
`aime2025`	software	healthy	`tests/aime2025`
`vimgolf_challenges`	software	healthy	`tests/vimgolf_challenges`
`boolq`	software	healthy	`tests/boolq`
`mmiu`	software	healthy	`tests/mmiu`
`b3`	software	healthy	`tests/b3`
`mask`	software	healthy	`tests/mask`
`mind2web`	software	healthy	`tests/mind2web`
`cyberseceval_4`	software	healthy	`tests/cyberseceval_4`
`vstar_bench`	software	healthy	`tests/vstar_bench`
`hle`	software	healthy	`tests/hle`
`gdpval`	software	healthy	`tests/gdpval`
`register_tooling`	software	healthy	`tests/register_tooling`
`mmlu`	software	healthy	`tests/mmlu`
`mmmu`	software	healthy	`tests/mmmu`
`sosbench`	software	healthy	`tests/sosbench`
`class_eval`	software	healthy	`tests/class_eval`
`worldsense`	software	healthy	`tests/worldsense`
`mind2web_sc`	software	healthy	`tests/mind2web_sc`
`swe_lancer`	software	healthy	`tests/swe_lancer`
`gpqa`	software	healthy	`tests/gpqa`
`sciknoweval`	software	healthy	`tests/sciknoweval`
`utils`	software	healthy	`tests/utils`
`test_artifacts`	software	healthy	`tests/utils/test_artifacts`
`humaneval`	software	healthy	`tests/humaneval`
`fortress`	software	healthy	`tests/fortress`
`gaia`	software	healthy	`tests/gaia`
`arc`	software	healthy	`tests/arc`
`frontierscience`	software	healthy	`tests/frontierscience`
`gdm_self_reasoning`	software	healthy	`tests/gdm_self_reasoning`
`kernelbench`	software	healthy	`tests/kernelbench`
`air_bench`	software	healthy	`tests/air_bench`
`simpleqa`	software	healthy	`tests/simpleqa`
`assistant_bench`	software	healthy	`tests/assistant_bench`
`bfcl`	software	healthy	`tests/bfcl`
`fixtures`	software	healthy	`tests/bfcl/fixtures`

Showing first 50 of this kind. Full payload available via the JSON button at the top of the page.

Showing first 50 of this kind. Full payload available via the JSON button at the top of the page.

Label	Layer	Status	Path
`prepare`	cicd	healthy	`.github/workflows/weekly-release.yml`
`review`	cicd	healthy	`.github/workflows/claude-review.yaml`
`check-pr-template`	cicd	healthy	`.github/workflows/pr-template-check.yml`
`validate`	cicd	healthy	`.github/workflows/register-submission.yaml`
`programmatic-checks`	cicd	healthy	`.github/workflows/register-submission.yaml`
`eval-validity`	cicd	healthy	`.github/workflows/register-submission.yaml`
`claude-review`	cicd	healthy	`.github/workflows/register-submission.yaml`
`await-manual-review`	cicd	healthy	`.github/workflows/register-submission.yaml`
`lint-all-evals`	cicd	healthy	`.github/workflows/lint-new-evals.yml`
`deploy`	cicd	healthy	`.github/workflows/docs-preview.yml`
`render`	cicd	healthy	`.github/workflows/docs.yml`
`publish`	cicd	healthy	`.github/workflows/docs.yml`
`submit`	cicd	healthy	`.github/workflows/register-issue-submission.yaml`
`lint`	cicd	healthy	`.github/workflows/workflow-lint.yml`
`run-readme-check`	cicd	healthy	`.github/workflows/checks.yml`
`posix-code-check`	cicd	healthy	`.github/workflows/checks.yml`
`ruff`	cicd	healthy	`.github/workflows/checks.yml`
`mypy`	cicd	healthy	`.github/workflows/checks.yml`
`package`	cicd	healthy	`.github/workflows/checks.yml`
`workflow-scripts-tests`	cicd	healthy	`.github/workflows/checks.yml`
`prepare`	cicd	healthy	`.github/workflows/docker-image-rebuild.yml`
`docker-build`	cicd	healthy	`.github/workflows/docker-image-rebuild.yml`
`publish-manifests`	cicd	healthy	`.github/workflows/docker-image-rebuild.yml`
`markdownlint`	cicd	healthy	`.github/workflows/markdown-lint.yml`
`publish`	cicd	healthy	`.github/workflows/publish.yaml`
`build-repo-context`	cicd	healthy	`.github/workflows/build-repo-context.yaml`
`trigger-tests`	cicd	healthy	`.github/workflows/build.yml`
`impact`	cicd	healthy	`.github/workflows/dep-bump-impact.yml`
`solve-issue`	cicd	healthy	`.github/workflows/claude-issue-solver.yaml`
`fix-pr`	cicd	healthy	`.github/workflows/claude-issue-solver.yaml`
`eval-validity`	cicd	healthy	`.github/workflows/register-submission-eval-validity.yaml`
`release`	cicd	healthy	`.github/workflows/release-on-merge.yml`
`notify`	cicd	healthy	`.github/workflows/release-on-merge.yml`
`scorecard`	cicd	healthy	`.github/workflows/register-submission-programmatic-checks.y…`
`fix-from-ci`	cicd	healthy	`.github/workflows/claude-fix-tests.yaml`
`fix-from-review`	cicd	healthy	`.github/workflows/claude-fix-tests.yaml`
`parse-smoke-failures`	cicd	healthy	`.github/workflows/claude-fix-tests.yaml`
`fix-smoke-failure`	cicd	healthy	`.github/workflows/claude-fix-tests.yaml`

Label	Layer	Status	Path
`ANY /`	api	healthy	`src/inspect_evals/cybench/challenges/locktalk/images/victim…`
`ANY /get_ticket`	api	healthy	`src/inspect_evals/cybench/challenges/locktalk/images/victim…`
`ANY /chat/<int:chat_id>`	api	healthy	`src/inspect_evals/cybench/challenges/locktalk/images/victim…`
`ANY /flag`	api	healthy	`src/inspect_evals/cybench/challenges/locktalk/images/victim…`
`ANY /assets/<path:path>`	api	healthy	`src/inspect_evals/cybench/challenges/glacier_exchange/image…`
`ANY /api/data/fetch/<path:coin>`	api	healthy	`src/inspect_evals/cybench/challenges/glacier_exchange/image…`
`ANY /api/wallet/transaction`	api	healthy	`src/inspect_evals/cybench/challenges/glacier_exchange/image…`
`ANY /api/wallet/join_glacier_club`	api	healthy	`src/inspect_evals/cybench/challenges/glacier_exchange/image…`
`ANY /api/wallet/balances`	api	healthy	`src/inspect_evals/cybench/challenges/glacier_exchange/image…`
`ANY /api/fetch_coins`	api	healthy	`src/inspect_evals/cybench/challenges/glacier_exchange/image…`
`ANY /api/options`	api	healthy	`src/inspect_evals/cybench/challenges/flag_command/images/vi…`
`ANY /api/monitor`	api	healthy	`src/inspect_evals/cybench/challenges/flag_command/images/vi…`
`ANY /signup`	api	healthy	`src/inspect_evals/cybench/challenges/chunky/images/blog/src…`
`ANY /login`	api	healthy	`src/inspect_evals/cybench/challenges/chunky/images/blog/src…`
`ANY /logout`	api	healthy	`src/inspect_evals/cybench/challenges/chunky/images/blog/src…`
`ANY /create_post`	api	healthy	`src/inspect_evals/cybench/challenges/chunky/images/blog/src…`
`ANY /post/<user_id>/<post_id>`	api	healthy	`src/inspect_evals/cybench/challenges/chunky/images/blog/src…`
`ANY /<user_id>/.well-known/jwks.json`	api	healthy	`src/inspect_evals/cybench/challenges/chunky/images/blog/src…`
`POST /submit-vulnerable`	api	healthy	`src/inspect_evals/cybergym/task_template/controller/server.…`
`POST /submit-fixed`	api	healthy	`src/inspect_evals/cybergym/task_template/controller/server.…`
`GET /health`	api	healthy	`src/inspect_evals/cti_realm/docker/mitre_service/mitre_api.…`
`GET /search/{keyword}`	api	healthy	`src/inspect_evals/cti_realm/docker/mitre_service/mitre_api.…`
`GET /tactic/{tactic}`	api	healthy	`src/inspect_evals/cti_realm/docker/mitre_service/mitre_api.…`
`ANY /models`	api	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/sqli/app.py`
`ANY /sample`	api	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/sqli/app.py`
`ANY /users`	api	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/sqli/app.py`
`ANY /users/<login>`	api	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/sqli/app.py`
`ANY /home`	api	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/idor/app.py`
`ANY /accounts`	api	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/idor/app.py`
`ANY /creds`	api	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/idor/app.py`
`ANY /creds/<account_id>`	api	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/idor/app.py`
`ANY /network`	api	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/cmd_injection…`
`ANY /about`	api	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/cmd_injection…`

Label	Layer	Status	Path
`10.0.0.1`	network	healthy	`tests/cyberseceval_4/test_e2e.py`
`10.0.0.2`	network	healthy	`tests/cyberseceval_4/test_e2e.py`
`192.168.1.100`	network	healthy	`tests/paperbench/score/test_utils.py`
`127.0.0.1`	network	healthy	`tests/livecodebench_pro/test_judge.py`
`8.8.8.8`	network	healthy	`src/inspect_evals/cybench/challenges/it_has_begun/resources…`
`128.90.59.19`	network	healthy	`src/inspect_evals/cybench/challenges/it_has_begun/resources…`
`4.13.0.0`	network	healthy	`src/inspect_evals/cybench/challenges/randsubware/solution/r…`
`35.196.65.151`	network	healthy	`src/inspect_evals/cybench/challenges/eval_me/resources/extr…`
`192.168.1.1`	network	healthy	`src/inspect_evals/tau2/telecom/TelecomUserTools.py`
`12.4.5.8`	network	healthy	`src/inspect_evals/mlrc_bench/orig_benchmark_corrections/met…`
`9.1.0.70`	network	healthy	`src/inspect_evals/mlrc_bench/orig_benchmark_corrections/met…`
`11.2.1.3`	network	healthy	`src/inspect_evals/mlrc_bench/orig_benchmark_corrections/met…`
`10.3.5.147`	network	healthy	`src/inspect_evals/mlrc_bench/orig_benchmark_corrections/met…`
`11.6.1.9`	network	healthy	`src/inspect_evals/mlrc_bench/orig_benchmark_corrections/met…`
`12.3.1.170`	network	healthy	`src/inspect_evals/mlrc_bench/orig_benchmark_corrections/met…`
`24.04.9.2`	network	healthy	`src/inspect_evals/theagentcompany/tasks/admin_watch_video/c…`
`17.172.224.47`	network	healthy	`src/inspect_evals/agentharm/benchmark/harmful_grading_funct…`
`192.168.0.12`	network	healthy	`src/inspect_evals/agentharm/benchmark/benign_tools/terminal…`
`192.168.0.10`	network	healthy	`src/inspect_evals/agentharm/benchmark/benign_tools/terminal…`
`192.168.1.15`	network	healthy	`src/inspect_evals/agentharm/benchmark/benign_tools/terminal…`
`192.168.1.255`	network	healthy	`src/inspect_evals/agentharm/benchmark/benign_tools/terminal…`
`255.255.255.0`	network	healthy	`src/inspect_evals/agentharm/benchmark/benign_tools/terminal…`
`192.168.1.0`	network	healthy	`src/inspect_evals/agentharm/benchmark/benign_tools/terminal…`
`203.0.113.50`	network	healthy	`src/inspect_evals/agentharm/benchmark/benign_tools/terminal…`
`17.58.100.1`	network	healthy	`src/inspect_evals/agentharm/benchmark/benign_tools/get_webp…`
`192.0.2.255`	network	healthy	`src/inspect_evals/agentharm/benchmark/benign_tools/get_webp…`
`31.13.79.246`	network	healthy	`src/inspect_evals/agentharm/benchmark/benign_tools/get_webp…`
`13.77.161.179`	network	healthy	`src/inspect_evals/agentharm/benchmark/benign_tools/get_webp…`
`2.6.2.1`	network	healthy	`src/inspect_evals/agentharm/benchmark/harmful_tools/termina…`

Label	Layer	Status	Path
`port:8888`	network	healthy	`src/inspect_evals/gdpval/Dockerfile`
`port:256`	network	healthy	`src/inspect_evals/cybench/agent_sandbox/Dockerfile`
`port:99`	network	healthy	`src/inspect_evals/cybench/agent_sandbox/Dockerfile`
`port:1337`	network	healthy	`src/inspect_evals/cybench/challenges/locktalk/images/victim…`
`port:8080`	network	healthy	`src/inspect_evals/cybench/challenges/glacier_exchange/image…`
`port:9999`	network	healthy	`src/inspect_evals/cybench/challenges/randsubware/images/vic…`
`port:151`	network	healthy	`src/inspect_evals/cybench/challenges/eval_me/resources/extr…`
`port:30899`	network	healthy	`src/inspect_evals/cybench/challenges/eval_me/resources/extr…`
`port:2000`	network	healthy	`src/inspect_evals/threecb/task_configs/find_all_users/setup…`
`port:5000`	network	healthy	`src/inspect_evals/threecb/task_configs/nmap/app.py`
`port:1000`	network	healthy	`src/inspect_evals/mlrc_bench/Dockerfile`
`port:9090`	network	healthy	`src/inspect_evals/livecodebench_pro/compose.yaml`
`port:17`	network	healthy	`src/inspect_evals/theagentcompany/tasks/hr_check_attendance…`
`port:30`	network	healthy	`src/inspect_evals/theagentcompany/tasks/hr_check_attendance…`
`port:18`	network	healthy	`src/inspect_evals/theagentcompany/tasks/hr_check_attendance…`
`port:65`	network	healthy	`src/inspect_evals/cti_realm/docker/compose.yaml`
`port:1001`	network	healthy	`src/inspect_evals/cti_realm/docker/compose.yaml`
`port:8081`	network	healthy	`src/inspect_evals/cti_realm/docker/mitre_service/mitre_api.…`
`port:80`	network	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/sqli/app.py`
`port:22`	network	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/ssh/Dockerfile`
`port:8082`	network	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/spray/app.py`
`port:3000`	network	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/grafana/Docke…`

Label	Layer	Status	Path
`gha::weekly-release`	cicd	healthy	`.github/workflows/weekly-release.yml`
`gha::claude-review`	cicd	healthy	`.github/workflows/claude-review.yaml`
`gha::pr-template-check`	cicd	healthy	`.github/workflows/pr-template-check.yml`
`gha::register-submission`	cicd	healthy	`.github/workflows/register-submission.yaml`
`gha::lint-new-evals`	cicd	healthy	`.github/workflows/lint-new-evals.yml`
`gha::docs-preview`	cicd	healthy	`.github/workflows/docs-preview.yml`
`gha::docs`	cicd	healthy	`.github/workflows/docs.yml`
`gha::register-issue-submission`	cicd	healthy	`.github/workflows/register-issue-submission.yaml`
`gha::workflow-lint`	cicd	healthy	`.github/workflows/workflow-lint.yml`
`gha::checks`	cicd	healthy	`.github/workflows/checks.yml`
`gha::docker-image-rebuild`	cicd	healthy	`.github/workflows/docker-image-rebuild.yml`
`gha::markdown-lint`	cicd	healthy	`.github/workflows/markdown-lint.yml`
`gha::publish`	cicd	healthy	`.github/workflows/publish.yaml`
`gha::build-repo-context`	cicd	healthy	`.github/workflows/build-repo-context.yaml`
`gha::build`	cicd	healthy	`.github/workflows/build.yml`
`gha::dep-bump-impact`	cicd	healthy	`.github/workflows/dep-bump-impact.yml`
`gha::claude-issue-solver`	cicd	healthy	`.github/workflows/claude-issue-solver.yaml`
`gha::register-submission-eval-validity`	cicd	healthy	`.github/workflows/register-submission-eval-validity.yaml`
`gha::release-on-merge`	cicd	healthy	`.github/workflows/release-on-merge.yml`
`gha::register-submission-programmatic-checks`	cicd	healthy	`.github/workflows/register-submission-programmatic-checks.y…`
`gha::claude-fix-tests`	cicd	healthy	`.github/workflows/claude-fix-tests.yaml`

Label	Layer	Status	Path
`password_literal::src/inspect_evals/agentdojo/task_suites/b…`	security	healthy	`src/inspect_evals/agentdojo/task_suites/banking/injection_t…`
`password_literal::src/inspect_evals/agentdojo/task_suites/b…`	security	healthy	`src/inspect_evals/agentdojo/task_suites/banking/user_tasks.…`
`password_literal::src/inspect_evals/cyberseceval_4/insecure…`	security	healthy	`src/inspect_evals/cyberseceval_4/insecure_code_detector/rul…`
`password_literal::src/inspect_evals/gdm_stealth/solver/stra…`	security	healthy	`src/inspect_evals/gdm_stealth/solver/strategic_rule_breakin…`
`password_literal::src/inspect_evals/gdm_stealth/solver/stra…`	security	healthy	`src/inspect_evals/gdm_stealth/solver/strategic_rule_breakin…`
`password_literal::src/inspect_evals/theagentcompany/tasks/h…`	security	healthy	`src/inspect_evals/theagentcompany/tasks/hr_populate_salary_…`
`password_literal::src/inspect_evals/theagentcompany/tasks/h…`	security	healthy	`src/inspect_evals/theagentcompany/tasks/hr_populate_salary_…`
`password_literal::src/inspect_evals/theagentcompany/tasks/h…`	security	healthy	`src/inspect_evals/theagentcompany/tasks/hr_populate_salary_…`
`password_literal::src/inspect_evals/theagentcompany/tasks/h…`	security	healthy	`src/inspect_evals/theagentcompany/tasks/hr_salary_analysis/…`
`generic_api_key::src/inspect_evals/cybergym/scorers.py`	security	healthy	`src/inspect_evals/cybergym/scorers.py`
`generic_api_key::src/inspect_evals/cybergym/task_template/c…`	security	healthy	`src/inspect_evals/cybergym/task_template/controller/server.…`
`github_token::src/inspect_evals/agentharm/benchmark/benign_…`	security	healthy	`src/inspect_evals/agentharm/benchmark/benign_grading_functi…`
`github_token::src/inspect_evals/agentharm/benchmark/harmful…`	security	healthy	`src/inspect_evals/agentharm/benchmark/harmful_grading_funct…`
`openai_or_anthropic_key::src/inspect_evals/agentharm/benchm…`	security	healthy	`src/inspect_evals/agentharm/benchmark/benign_tools/terminal…`
`openai_or_anthropic_key::src/inspect_evals/agentharm/benchm…`	security	healthy	`src/inspect_evals/agentharm/benchmark/benign_tools/terminal…`
`github_token::src/inspect_evals/agentharm/benchmark/benign_…`	security	healthy	`src/inspect_evals/agentharm/benchmark/benign_tools/content/…`
`openai_or_anthropic_key::src/inspect_evals/agentharm/benchm…`	security	healthy	`src/inspect_evals/agentharm/benchmark/harmful_tools/termina…`
`openai_or_anthropic_key::src/inspect_evals/agentharm/benchm…`	security	healthy	`src/inspect_evals/agentharm/benchmark/harmful_tools/termina…`
`github_token::src/inspect_evals/agentharm/benchmark/harmful…`	security	healthy	`src/inspect_evals/agentharm/benchmark/harmful_tools/content…`

Label	Layer	Status	Path
`SLACK_WEBHOOK_URL`	cicd	healthy	`—`
`INSPECT_COMMUNITY_SLACK_WEBHOOK_URL`	cicd	healthy	`—`
`ARCADIA_GHCR_TOKEN`	cicd	healthy	`—`
`SEMANTIC_SCHOLAR_API_KEY`	cicd	healthy	`—`
`INSPECT_EVALS_DISPATCH_TOKEN`	cicd	healthy	`—`
`PR_NUMBER`	cicd	healthy	`—`
`ARCADIA_GHCR_USERNAME`	cicd	healthy	`—`
`ANTHROPIC_ROLE_ARN`	cicd	healthy	`—`
`GITHUB_TOKEN`	cicd	healthy	`—`
`REGISTER_SLACK_WEBHOOK_URL`	cicd	healthy	`—`
`APP_PRIVATE_KEY`	cicd	healthy	`—`
`APP_ID`	cicd	healthy	`—`
`ANTHROPIC_API_KEY`	cicd	healthy	`—`

Label	Layer	Status	Path
`products`	data	healthy	`src/inspect_evals/theagentcompany/tasks/ds_sql_exercise/ini…`
`models`	data	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/sqli/app.sql`
`users`	data	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/sqli/app.sql`
`members`	data	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/pw_reuse/db.s…`
`posts`	data	healthy	`src/inspect_evals/gdm_in_house_ctf/challenges/pw_reuse/db.s…`
`transactions`	data	healthy	`src/inspect_evals/gdm_self_reasoning/common_tools.py`
`blog_posts`	data	healthy	`src/inspect_evals/cybench/challenges/chunky/images/blog/src…`

Label	Layer	Status	Path
`postgres`	data	healthy	`tests/utils/test_docker_utils.py`
`postgresql`	data	healthy	`tests/bfcl/test_solver.py`
`sqlite`	data	healthy	`tools/run_evals.py`
`mysql`	data	healthy	`src/inspect_evals/cyberseceval_4/insecure_code_detector/rul…`
`cassandra`	data	healthy	`src/inspect_evals/cyberseceval_4/insecure_code_detector/rul…`
`mongodb`	data	healthy	`src/inspect_evals/cyberseceval_4/insecure_code_detector/rul…`

Label	Layer	Status	Path
`vps::azure`	hardware	healthy	`README.md`
`vps::aws`	hardware	healthy	`README.md`
`vps::gcp`	hardware	healthy	`tests/gdm_self_proliferation/test_dataset_utils.py`
`vps::ec2`	hardware	healthy	`src/inspect_evals/gdpval/README.md`

Label	Layer	Status	Path
`haproxy`	network	healthy	`ASSETS.yaml`
`nginx`	network	healthy	`.pre-commit-config.yaml`

Label	Layer	Status	Path
`UKGovernmentBEIS__inspect_evals`	software	healthy	`/data/fable5_failed_archive/UKGovernmentBEIS__inspect_evals`

Label	Layer	Status	Path
`celery`	data	healthy	`tests/sosbench/test_utils.py`

Label	Layer	Status	Path
`gpu (detected)`	hardware	healthy	`ASSETS.yaml`

For AI agents: Voting guide (TP/FP) MCP manifest Stdio wrapper SARIF Integrate Findings queue Vote TP/FP on findings to calibrate the engine.

For AI agents + API integrations

Email me when this repo regresses

Free. We re-scan periodically; new criticals → your inbox. No signup required for the scan itself.

API access

This page is publicly accessible at: https://repobility.com/scan/13d59e23-a6db-41ca-bf82-51b9ab36f8d1/

To check status programmatically (no auth required):

curl -s https://repobility.com/api/v1/public/scan/13d59e23-a6db-41ca-bf82-51b9ab36f8d1/

Important — please don't re-submit the same URL repeatedly. The submission endpoint is idempotent: re-submitting the same git URL returns this same scan_token, not a new one. To re-scan this repo, sign up free and use the dashboard.

Label	Layer	Status	Path
`image::tests/utils/test_artifacts/Dockerfile`	hardware	healthy	`tests/utils/test_artifacts/Dockerfile`
`image::src/inspect_evals/vimgolf_challenges/Dockerfile`	hardware	healthy	`src/inspect_evals/vimgolf_challenges/Dockerfile`
`image::src/inspect_evals/gdpval/Dockerfile`	hardware	healthy	`src/inspect_evals/gdpval/Dockerfile`
`image::src/inspect_evals/class_eval/Dockerfile`	hardware	healthy	`src/inspect_evals/class_eval/Dockerfile`
`image::src/inspect_evals/kernelbench/Dockerfile`	hardware	healthy	`src/inspect_evals/kernelbench/Dockerfile`
`image::src/inspect_evals/scbench/Dockerfile`	hardware	healthy	`src/inspect_evals/scbench/Dockerfile`
`image::src/inspect_evals/cybench/agent_sandbox/Dockerfile`	hardware	healthy	`src/inspect_evals/cybench/agent_sandbox/Dockerfile`
`image::src/inspect_evals/cybench/challenges/locktalk/images…`	hardware	healthy	`src/inspect_evals/cybench/challenges/locktalk/images/victim…`
`image::src/inspect_evals/cybench/challenges/glacier_exchang…`	hardware	healthy	`src/inspect_evals/cybench/challenges/glacier_exchange/image…`
`image::src/inspect_evals/cybench/challenges/frog_waf/images…`	hardware	healthy	`src/inspect_evals/cybench/challenges/frog_waf/images/victim…`
`image::src/inspect_evals/cybench/challenges/skilift/images/…`	hardware	healthy	`src/inspect_evals/cybench/challenges/skilift/images/victim/…`
`image::src/inspect_evals/cybench/challenges/were_pickle_phr…`	hardware	healthy	`src/inspect_evals/cybench/challenges/were_pickle_phreaks_re…`
`image::src/inspect_evals/cybench/challenges/randsubware/ima…`	hardware	healthy	`src/inspect_evals/cybench/challenges/randsubware/images/vic…`
`image::src/inspect_evals/cybench/challenges/noisier_crc/ima…`	hardware	healthy	`src/inspect_evals/cybench/challenges/noisier_crc/images/vic…`
`image::src/inspect_evals/cybench/challenges/failproof/image…`	hardware	healthy	`src/inspect_evals/cybench/challenges/failproof/images/victi…`
`image::src/inspect_evals/cybench/challenges/robust_cbc/imag…`	hardware	healthy	`src/inspect_evals/cybench/challenges/robust_cbc/images/vict…`
`image::src/inspect_evals/cybench/challenges/flag_command/im…`	hardware	healthy	`src/inspect_evals/cybench/challenges/flag_command/images/vi…`
`image::src/inspect_evals/cybench/challenges/back_to_the_pas…`	hardware	healthy	`src/inspect_evals/cybench/challenges/back_to_the_past/image…`
`image::src/inspect_evals/cybench/challenges/diffecient/imag…`	hardware	healthy	`src/inspect_evals/cybench/challenges/diffecient/images/vict…`
`image::src/inspect_evals/cybench/challenges/shuffled_aes/im…`	hardware	healthy	`src/inspect_evals/cybench/challenges/shuffled_aes/images/vi…`
`image::src/inspect_evals/cybench/challenges/delulu/images/v…`	hardware	healthy	`src/inspect_evals/cybench/challenges/delulu/images/victim/D…`
`image::src/inspect_evals/cybench/challenges/just_another_pi…`	hardware	healthy	`src/inspect_evals/cybench/challenges/just_another_pickle_ja…`
`image::src/inspect_evals/cybench/challenges/network_tools/i…`	hardware	healthy	`src/inspect_evals/cybench/challenges/network_tools/images/v…`
`image::src/inspect_evals/cybench/challenges/walking_to_the_…`	hardware	healthy	`src/inspect_evals/cybench/challenges/walking_to_the_sea_sid…`
`image::src/inspect_evals/cybench/challenges/labyrinth_lingu…`	hardware	healthy	`src/inspect_evals/cybench/challenges/labyrinth_linguist/ima…`
`image::src/inspect_evals/cybench/challenges/avatar/images/v…`	hardware	healthy	`src/inspect_evals/cybench/challenges/avatar/images/victim/D…`
`image::src/inspect_evals/cybench/challenges/chunky/images/n…`	hardware	healthy	`src/inspect_evals/cybench/challenges/chunky/images/nginx/Do…`
`image::src/inspect_evals/cybench/challenges/chunky/images/r…`	hardware	healthy	`src/inspect_evals/cybench/challenges/chunky/images/rcache/D…`
`image::src/inspect_evals/cybench/challenges/chunky/images/b…`	hardware	healthy	`src/inspect_evals/cybench/challenges/chunky/images/blog/Doc…`
`image::src/inspect_evals/cybench/challenges/noisy_crc/image…`	hardware	healthy	`src/inspect_evals/cybench/challenges/noisy_crc/images/victi…`
`image::src/inspect_evals/cybench/challenges/ezmaze/images/v…`	hardware	healthy	`src/inspect_evals/cybench/challenges/ezmaze/images/victim/D…`
`image::src/inspect_evals/cybench/challenges/unbreakable/ima…`	hardware	healthy	`src/inspect_evals/cybench/challenges/unbreakable/images/vic…`
`image::src/inspect_evals/threecb/task_configs/evasion_debug…`	hardware	healthy	`src/inspect_evals/threecb/task_configs/evasion_debugger/Doc…`
`image::src/inspect_evals/threecb/task_configs/web_navigatio…`	hardware	healthy	`src/inspect_evals/threecb/task_configs/web_navigation/Docke…`
`image::src/inspect_evals/threecb/task_configs/resourcedevel…`	hardware	healthy	`src/inspect_evals/threecb/task_configs/resourcedevelopment_…`
`image::src/inspect_evals/threecb/task_configs/python_repl_f…`	hardware	healthy	`src/inspect_evals/threecb/task_configs/python_repl_factoria…`
`image::src/inspect_evals/threecb/task_configs/escalation_se…`	hardware	healthy	`src/inspect_evals/threecb/task_configs/escalation_setuid/Do…`
`image::src/inspect_evals/threecb/task_configs/find_all_user…`	hardware	healthy	`src/inspect_evals/threecb/task_configs/find_all_users/Docke…`
`image::src/inspect_evals/threecb/task_configs/binpwn_gdb_re…`	hardware	healthy	`src/inspect_evals/threecb/task_configs/binpwn_gdb_repl/Dock…`
`image::src/inspect_evals/threecb/task_configs/impact_defaci…`	hardware	healthy	`src/inspect_evals/threecb/task_configs/impact_defacing/Dock…`
`image::src/inspect_evals/threecb/task_configs/nmap/Dockerfi…`	hardware	healthy	`src/inspect_evals/threecb/task_configs/nmap/Dockerfile`
`image::src/inspect_evals/threecb/task_configs/initialaccess…`	hardware	healthy	`src/inspect_evals/threecb/task_configs/initialaccess_mail_l…`
`image::src/inspect_evals/threecb/task_configs/null_writing/…`	hardware	healthy	`src/inspect_evals/threecb/task_configs/null_writing/Dockerf…`
`image::src/inspect_evals/bigcodebench/Dockerfile`	hardware	healthy	`src/inspect_evals/bigcodebench/Dockerfile`
`image::src/inspect_evals/gdm_stealth/Dockerfile`	hardware	healthy	`src/inspect_evals/gdm_stealth/Dockerfile`
`image::src/inspect_evals/ifevalcode/Dockerfile`	hardware	healthy	`src/inspect_evals/ifevalcode/Dockerfile`
`image::src/inspect_evals/cyberseceval_2/vulnerability_explo…`	hardware	healthy	`src/inspect_evals/cyberseceval_2/vulnerability_exploit/Dock…`
`image::src/inspect_evals/mlrc_bench/Dockerfile`	hardware	healthy	`src/inspect_evals/mlrc_bench/Dockerfile`
`image::src/inspect_evals/paperbench/images/Dockerfile`	hardware	healthy	`src/inspect_evals/paperbench/images/Dockerfile`
`image::src/inspect_evals/compute_eval/Dockerfile`	hardware	healthy	`src/inspect_evals/compute_eval/Dockerfile`

Label	Layer	Status	Path
`auth::src/inspect_evals/cybench/challenges/locktalk/images/…`	security	healthy	`src/inspect_evals/cybench/challenges/locktalk/images/victim…`
`auth::.github/workflows/register-submission.yaml`	security	healthy	`.github/workflows/register-submission.yaml`
`auth::src/inspect_evals/agentharm/benchmark/benign_tools/qu…`	security	healthy	`src/inspect_evals/agentharm/benchmark/benign_tools/query_bi…`
`auth::src/inspect_evals/cybench/challenges/locktalk/images/…`	security	healthy	`src/inspect_evals/cybench/challenges/locktalk/images/victim…`
`auth::src/inspect_evals/agentharm/benchmark/benign_tools/qu…`	security	healthy	`src/inspect_evals/agentharm/benchmark/benign_tools/query_on…`
`auth::src/inspect_evals/cybench/challenges/chunky/solution/…`	security	healthy	`src/inspect_evals/cybench/challenges/chunky/solution/solve.…`
`auth::.github/workflows/publish.yaml`	security	healthy	`.github/workflows/publish.yaml`
`auth::src/inspect_evals/agentharm/benchmark/harmful_tools/g…`	security	healthy	`src/inspect_evals/agentharm/benchmark/harmful_tools/get_web…`
`auth::.github/workflows/register-issue-submission.yaml`	security	healthy	`.github/workflows/register-issue-submission.yaml`
`auth::src/inspect_evals/theagentcompany/tasks/admin_mass_fo…`	security	healthy	`src/inspect_evals/theagentcompany/tasks/admin_mass_forms_fi…`
`auth::src/inspect_evals/cybench/challenges/chunky/images/bl…`	security	healthy	`src/inspect_evals/cybench/challenges/chunky/images/blog/src…`
`auth::src/inspect_evals/cybench/challenges/locktalk/images/…`	security	healthy	`src/inspect_evals/cybench/challenges/locktalk/images/victim…`
`auth::.github/workflows/claude-issue-solver.yaml`	security	healthy	`.github/workflows/claude-issue-solver.yaml`
`auth::.github/workflows/claude-review.yaml`	security	healthy	`.github/workflows/claude-review.yaml`
`auth::src/register_tooling/deriver.py`	security	healthy	`src/register_tooling/deriver.py`
`auth::src/inspect_evals/agentharm/benchmark/benign_tools/ge…`	security	healthy	`src/inspect_evals/agentharm/benchmark/benign_tools/get_webp…`
`auth::.github/workflows/register-submission-eval-validity.y…`	security	healthy	`.github/workflows/register-submission-eval-validity.yaml`
`auth::.github/actions/claude-setup/action.yaml`	security	healthy	`.github/actions/claude-setup/action.yaml`
`auth::src/inspect_evals/agentharm/benchmark/harmful_tools/q…`	security	healthy	`src/inspect_evals/agentharm/benchmark/harmful_tools/query_o…`
`auth::src/inspect_evals/cybench/challenges/locktalk/images/…`	security	healthy	`src/inspect_evals/cybench/challenges/locktalk/images/victim…`
`auth::.github/workflows/claude-fix-tests.yaml`	security	healthy	`.github/workflows/claude-fix-tests.yaml`
`auth::src/inspect_evals/agentdojo/tools/travel_booking_clie…`	security	healthy	`src/inspect_evals/agentdojo/tools/travel_booking_client.py`
`auth::src/inspect_evals/agentdojo/task_suites/travel/inject…`	security	healthy	`src/inspect_evals/agentdojo/task_suites/travel/injection_ta…`
`auth::.github/workflows/build-repo-context.yaml`	security	healthy	`.github/workflows/build-repo-context.yaml`
`auth::src/inspect_evals/agentharm/benchmark/harmful_grading…`	security	healthy	`src/inspect_evals/agentharm/benchmark/harmful_grading_funct…`

UKGovernmentBEIS/inspect_evals

Complete repo analysis

function 50+

file 50+

class 50+

directory 50+

container 50+

job 38

endpoint 33

service 29

auth 25

port 22

pipeline 21

secret 19

env_var 13

table 7

database 6

vps 4

load_balancer 2

repo 1

queue 1

gpu 1