ggml-org/llama.cpp

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.

175 of your 249 findings came from Repobility's proprietary detections. ✓ Repobility tags below mark them.

Upstream (GitHub) caused delay on this scan — not Repobility.

GitHub API rate-limited (HTTP 403) — preflight skipped, fell back to direct git clone.
Clone from GitHub took 39.51s for a 145.1 MB repo slow.
Repobility's analysis ran in 37.43s after the clone landed.

https://github.com/ggml-org/llama.cpp · scanned 2026-06-05 05:22 UTC (1 week, 1 day ago) · 10 languages

925 raw signals (233 security + 692 graph) 11/13 scanners ran System graph score 72 (higher by 6)

File as issue Image

UNIFIED Repobility · multi-layer engine · AI coders

Complete repo analysis

Last scanned 1 week, 1 day ago · v2 · 243 actionable findings from 2 signal sources. 336 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 · 177 findings

Score breakdown â 2026-05-18-v5

Component	Sub-score	Weight	Contribution
`structure_score`	85.0	0.15	12.75
`security_score`	100.0	0.25	25.00
`testing_score`	53.0	0.20	10.60
`documentation_score`	77.0	0.15	11.55
`practices_score`	94.0	0.15	14.10
`code_quality`	45.0	0.10	4.50
Overall		1.00	78.5

security_score may be inflated — optional security scanners were skipped on this fast scan

Severity distribution — click a segment to filter

Active filters: excluding tests × Reset all

Severity: Critical 5 High 17 Medium 32 Low 129 9-Layer: Software Security Quality Integrity Frontend Hardware Data Network Cicd Source: Security checks 66 System graph 177 Crowd 0 Layer: Software 86 Quality 111 Security 16 Cicd 8 Api 1 Frontend 19 Network 2

Exclude dismissed / FP Exclude test files

All 5044 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
`download_file_with_auth`	software	healthy	`convert_hf_to_gguf_update.py:194`
`download_model`	software	healthy	`convert_hf_to_gguf_update.py:204`
`get_existing_models`	software	healthy	`convert_hf_to_gguf_update.py:248`
`__init__`	software	healthy	`convert_llama_ggml_to_gguf.py:204`
`set_n_ff`	software	healthy	`convert_llama_ggml_to_gguf.py:53`
`load`	software	healthy	`convert_llama_ggml_to_gguf.py:180`
`__str__`	software	healthy	`convert_llama_ggml_to_gguf.py:75`
`validate_header`	software	healthy	`convert_llama_ggml_to_gguf.py:145`
`validate_conversion`	software	healthy	`convert_llama_ggml_to_gguf.py:168`
`save`	software	healthy	`convert_llama_ggml_to_gguf.py:228`
`add_params`	software	healthy	`convert_llama_ggml_to_gguf.py:247`
`add_vocab`	software	healthy	`convert_llama_ggml_to_gguf.py:287`
`add_tensors`	software	healthy	`convert_llama_ggml_to_gguf.py:340`
`handle_metadata`	software	healthy	`convert_llama_ggml_to_gguf.py:360`
`handle_args`	software	healthy	`convert_llama_ggml_to_gguf.py:388`
`main`	software	healthy	`convert_llama_ggml_to_gguf.py:414`
`split_str_to_n_bytes`	software	healthy	`convert_hf_to_gguf.py:30`
`parse_args`	software	healthy	`convert_hf_to_gguf.py:48`
`main`	software	healthy	`convert_hf_to_gguf.py:162`
`__init__`	software	healthy	`convert_lora_to_gguf.py:406`
`get_lora_A_B`	software	healthy	`convert_lora_to_gguf.py:55`
`__getitem__`	software	healthy	`convert_lora_to_gguf.py:58`
`dtype`	software	healthy	`convert_lora_to_gguf.py:117`
`shape`	software	healthy	`convert_lora_to_gguf.py:122`
`size`	software	healthy	`convert_lora_to_gguf.py:126`
`contiguous`	software	healthy	`convert_lora_to_gguf.py:130`
`reshape`	software	healthy	`convert_lora_to_gguf.py:136`
`reshape_as`	software	healthy	`convert_lora_to_gguf.py:162`
`view`	software	healthy	`convert_lora_to_gguf.py:165`
`permute`	software	healthy	`convert_lora_to_gguf.py:168`
`transpose`	software	healthy	`convert_lora_to_gguf.py:181`
`swapaxes`	software	healthy	`convert_lora_to_gguf.py:187`
`split`	software	healthy	`convert_lora_to_gguf.py:190`
`to`	software	healthy	`convert_lora_to_gguf.py:208`
`__mul__`	software	healthy	`convert_lora_to_gguf.py:211`
`__rmul__`	software	healthy	`convert_lora_to_gguf.py:218`
`__torch_function__`	software	healthy	`convert_lora_to_gguf.py:222`
`get_base_tensor_name`	software	healthy	`convert_lora_to_gguf.py:269`
`parse_args`	software	healthy	`convert_lora_to_gguf.py:279`
`load_hparams_from_hf`	software	healthy	`convert_lora_to_gguf.py:322`
`set_vocab`	software	healthy	`convert_lora_to_gguf.py:413`
`set_type`	software	healthy	`convert_lora_to_gguf.py:416`
`set_gguf_parameters`	software	healthy	`convert_lora_to_gguf.py:420`
`generate_extra_tensors`	software	healthy	`convert_lora_to_gguf.py:447`
`get_tensors`	software	healthy	`convert_lora_to_gguf.py:451`
`modify_tensors`	software	healthy	`convert_lora_to_gguf.py:495`
`__init__`	software	healthy	`tests/test-tokenizer-random.py:160`
`_load_libllama_cffi`	software	healthy	`tests/test-tokenizer-random.py:41`
`model_default_params`	software	healthy	`tests/test-tokenizer-random.py:58`
`context_default_params`	software	healthy	`tests/test-tokenizer-random.py:64`

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

Label	Layer	Status	Path
`convert_hf_to_gguf_update.py`	software	healthy	`convert_hf_to_gguf_update.py`
`ty.toml`	software	healthy	`ty.toml`
`convert_llama_ggml_to_gguf.py`	software	healthy	`convert_llama_ggml_to_gguf.py`
`README.md`	software	healthy	`README.md`
`CLAUDE.md`	software	healthy	`CLAUDE.md`
`build-xcframework.sh`	software	healthy	`build-xcframework.sh`
`CONTRIBUTING.md`	software	healthy	`CONTRIBUTING.md`
`convert_hf_to_gguf.py`	software	healthy	`convert_hf_to_gguf.py`
`.pre-commit-config.yaml`	software	healthy	`.pre-commit-config.yaml`
`pyrightconfig.json`	software	healthy	`pyrightconfig.json`
`pyproject.toml`	software	healthy	`pyproject.toml`
`Makefile`	software	healthy	`Makefile`
`CMakePresets.json`	software	healthy	`CMakePresets.json`
`requirements.txt`	software	healthy	`requirements.txt`
`SECURITY.md`	software	healthy	`SECURITY.md`
`AGENTS.md`	software	healthy	`AGENTS.md`
`convert_lora_to_gguf.py`	software	healthy	`convert_lora_to_gguf.py`
`README.md`	software	healthy	`models/templates/README.md`
`test-mtmd-c-api.c`	software	healthy	`tests/test-mtmd-c-api.c`
`test-tokenizer-0.py`	software	warning	`tests/test-tokenizer-0.py`
`test-tokenizer-1-spm.cpp`	software	healthy	`tests/test-tokenizer-1-spm.cpp`
`export-graph-ops.cpp`	software	healthy	`tests/export-graph-ops.cpp`
`test-backend-sampler.cpp`	software	healthy	`tests/test-backend-sampler.cpp`
`test-tokenizer-0.cpp`	software	healthy	`tests/test-tokenizer-0.cpp`
`test-gguf-model-data.cpp`	software	healthy	`tests/test-gguf-model-data.cpp`
`test-backend-ops.cpp`	software	healthy	`tests/test-backend-ops.cpp`
`test-tokenizers-repo.sh`	software	healthy	`tests/test-tokenizers-repo.sh`
`test-opt.cpp`	software	healthy	`tests/test-opt.cpp`
`test-reasoning-budget.cpp`	software	healthy	`tests/test-reasoning-budget.cpp`
`test-json-partial.cpp`	software	healthy	`tests/test-json-partial.cpp`
`test-quant-type-selection.cpp`	software	healthy	`tests/test-quant-type-selection.cpp`
`test-quantize-stats.cpp`	software	healthy	`tests/test-quantize-stats.cpp`
`test-chat-template.cpp`	software	healthy	`tests/test-chat-template.cpp`
`test-gbnf-validator.cpp`	software	healthy	`tests/test-gbnf-validator.cpp`
`test-quantize-perf.cpp`	software	healthy	`tests/test-quantize-perf.cpp`
`test-arg-parser.cpp`	software	healthy	`tests/test-arg-parser.cpp`
`test-thread-safety.cpp`	software	healthy	`tests/test-thread-safety.cpp`
`gguf-model-data.cpp`	software	healthy	`tests/gguf-model-data.cpp`
`test-rope.cpp`	software	healthy	`tests/test-rope.cpp`
`test-model-load-cancel.cpp`	software	healthy	`tests/test-model-load-cancel.cpp`
`test-grammar-llguidance.cpp`	software	healthy	`tests/test-grammar-llguidance.cpp`
`test-regex-partial.cpp`	software	healthy	`tests/test-regex-partial.cpp`
`get-model.h`	software	healthy	`tests/get-model.h`
`test-sampling.cpp`	software	healthy	`tests/test-sampling.cpp`
`get-model.cpp`	software	healthy	`tests/get-model.cpp`
`test-log.cpp`	software	healthy	`tests/test-log.cpp`
`test-llama-grammar.cpp`	software	healthy	`tests/test-llama-grammar.cpp`
`test-chat-peg-parser.cpp`	software	healthy	`tests/test-chat-peg-parser.cpp`
`test-chat.cpp`	software	healthy	`tests/test-chat.cpp`
`test-jinja.cpp`	software	healthy	`tests/test-jinja.cpp`

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

Label	Layer	Status	Path
`TOKENIZER_TYPE`	software	healthy	`convert_hf_to_gguf_update.py:28`
`GGMLFormat`	software	healthy	`convert_llama_ggml_to_gguf.py:21`
`GGMLFType`	software	healthy	`convert_llama_ggml_to_gguf.py:27`
`Hyperparameters`	software	healthy	`convert_llama_ggml_to_gguf.py:47`
`Vocab`	software	healthy	`convert_llama_ggml_to_gguf.py:79`
`Tensor`	software	healthy	`convert_llama_ggml_to_gguf.py:101`
`GGMLModel`	software	healthy	`convert_llama_ggml_to_gguf.py:134`
`GGMLToGGUF`	software	healthy	`convert_llama_ggml_to_gguf.py:203`
`PartialLoraTensor`	software	healthy	`convert_lora_to_gguf.py:34`
`LoraTorchTensor`	software	healthy	`convert_lora_to_gguf.py:40`
`LoraModel`	software	healthy	`convert_lora_to_gguf.py:401`
`LibLlama`	software	healthy	`tests/test-tokenizer-random.py:28`
`LibLlamaModel`	software	healthy	`tests/test-tokenizer-random.py:71`
`Tokenizer`	software	healthy	`tests/test-tokenizer-random.py:119`
`TokenizerGroundtruth`	software	healthy	`tests/test-tokenizer-random.py:128`
`TokenizerLlamaCpp`	software	healthy	`tests/test-tokenizer-random.py:156`
`HuggingFaceModel`	software	healthy	`scripts/fetch_server_test_models.py:23`
`Config`	software	healthy	`scripts/fetch_server_test_models.py:27`
`DocsGenerator`	software	healthy	`scripts/create_ops_docs.py:13`
`LlamaBenchData`	software	healthy	`scripts/compare-llama-bench.py:215`
`LlamaBenchDataSQLite3`	software	healthy	`scripts/compare-llama-bench.py:322`
`LlamaBenchDataSQLite3File`	software	healthy	`scripts/compare-llama-bench.py:404`
`LlamaBenchDataJSONL`	software	healthy	`scripts/compare-llama-bench.py:457`
`LlamaBenchDataJSON`	software	healthy	`scripts/compare-llama-bench.py:492`
`LlamaBenchDataCSV`	software	healthy	`scripts/compare-llama-bench.py:530`
`DeviceUnavailableError`	software	healthy	`scripts/snapdragon/qdc/run_qdc_jobs.py:81`
`JobResult`	software	healthy	`scripts/snapdragon/qdc/run_qdc_jobs.py:127`
`Platform`	software	healthy	`scripts/snapdragon/qdc/run_qdc_jobs.py:235`
`PlatformSpec`	software	healthy	`scripts/snapdragon/qdc/run_qdc_jobs.py:241`
`LineNumberArea`	software	healthy	`scripts/jinja/jinja-tester.py:160`
`CodeEditor`	software	healthy	`scripts/jinja/jinja-tester.py:172`
`JinjaTester`	software	healthy	`scripts/jinja/jinja-tester.py:290`
`ggml_init_params`	software	healthy	`gguf-py/tests/test_quants.py:32`
`GGMLQuants`	software	healthy	`gguf-py/tests/test_quants.py:40`
`TestMetadataMethod`	software	healthy	`gguf-py/tests/test_metadata.py:15`
`ReaderField`	software	healthy	`gguf-py/gguf/gguf_reader.py:39`
`ReaderTensor`	software	healthy	`gguf-py/gguf/gguf_reader.py:100`
`GGUFReader`	software	healthy	`gguf-py/gguf/gguf_reader.py:111`
`Metadata`	software	healthy	`gguf-py/gguf/metadata.py:19`
`LazyMeta`	software	healthy	`gguf-py/gguf/lazy.py:14`
`LazyBase`	software	healthy	`gguf-py/gguf/lazy.py:77`
`LazyNumpyTensor`	software	healthy	`gguf-py/gguf/lazy.py:206`
`RemoteTensor`	software	healthy	`gguf-py/gguf/utility.py:79`
`SafetensorRemote`	software	healthy	`gguf-py/gguf/utility.py:93`
`LocalTensorRange`	software	healthy	`gguf-py/gguf/utility.py:274`
`LocalTensor`	software	healthy	`gguf-py/gguf/utility.py:281`
`SafetensorsLocal`	software	healthy	`gguf-py/gguf/utility.py:290`
`Keys`	software	healthy	`gguf-py/gguf/constants.py:20`
`General`	software	healthy	`gguf-py/gguf/constants.py:21`
`LLM`	software	healthy	`gguf-py/gguf/constants.py:103`

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

Label	Layer	Status	Path
`models`	software	healthy	`models`
`templates`	software	healthy	`models/templates`
`tests`	software	healthy	`tests`
`peg-parser`	software	healthy	`tests/peg-parser`
`common`	software	healthy	`common`
`jinja`	software	healthy	`common/jinja`
`docs`	software	healthy	`docs`
`development`	software	healthy	`docs/development`
`multimodal`	software	healthy	`docs/multimodal`
`backend`	software	healthy	`docs/backend`
`snapdragon`	software	healthy	`docs/backend/snapdragon`
`VirtGPU`	software	healthy	`docs/backend/VirtGPU`
`scripts`	software	healthy	`scripts`
`snapdragon`	software	healthy	`scripts/snapdragon`
`adb`	software	healthy	`scripts/snapdragon/adb`
`qdc`	software	healthy	`scripts/snapdragon/qdc`
`tests`	software	healthy	`scripts/snapdragon/qdc/tests`
`linux`	software	healthy	`scripts/snapdragon/qdc/tests/linux`
`hip`	software	healthy	`scripts/hip`
`apple`	software	healthy	`scripts/apple`
`jinja`	software	healthy	`scripts/jinja`
`pocs`	software	healthy	`pocs`
`vdot`	software	healthy	`pocs/vdot`
`app`	software	healthy	`app`
`gguf-py`	software	healthy	`gguf-py`
`tests`	software	healthy	`gguf-py/tests`
`gguf`	software	healthy	`gguf-py/gguf`
`scripts`	software	healthy	`gguf-py/gguf/scripts`
`examples`	software	healthy	`gguf-py/examples`
`grammars`	software	healthy	`grammars`
`examples`	software	healthy	`examples`
`parallel`	software	healthy	`examples/parallel`
`passkey`	software	healthy	`examples/passkey`
`simple`	software	healthy	`examples/simple`
`gguf-hash`	software	healthy	`examples/gguf-hash`
`deps`	software	healthy	`examples/gguf-hash/deps`
`rotate-bits`	software	healthy	`examples/gguf-hash/deps/rotate-bits`
`sha256`	software	healthy	`examples/gguf-hash/deps/sha256`
`xxhash`	software	healthy	`examples/gguf-hash/deps/xxhash`
`sha1`	software	healthy	`examples/gguf-hash/deps/sha1`
`lookahead`	software	healthy	`examples/lookahead`
`llama.android`	software	healthy	`examples/llama.android`
`app`	software	healthy	`examples/llama.android/app`
`src`	software	healthy	`examples/llama.android/app/src`
`main`	software	healthy	`examples/llama.android/app/src/main`
`java`	software	healthy	`examples/llama.android/app/src/main/java`
`com`	software	healthy	`examples/llama.android/app/src/main/java/com`
`example`	software	healthy	`examples/llama.android/app/src/main/java/com/example`
`llama`	software	healthy	`examples/llama.android/app/src/main/java/com/example/llama`
`lib`	software	healthy	`examples/llama.android/lib`

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

Label	Layer	Status	Path
`windows-msys2`	cicd	healthy	`.github/workflows/build-msys.yml`
`default`	cicd	healthy	`.github/workflows/build-android.yml`
`ndk`	cicd	healthy	`.github/workflows/build-android.yml`
`arm64`	cicd	healthy	`.github/workflows/build-android.yml`
`ubuntu-24-openvino`	cicd	healthy	`.github/workflows/build-openvino.yml`
`ubuntu-24-rpc`	cicd	healthy	`.github/workflows/build-rpc.yml`
`pre-tokenizer-hashes`	cicd	healthy	`.github/workflows/pre-tokenizer-hashes.yml`
`ubuntu-24-llguidance`	cicd	healthy	`.github/workflows/build-3rd-party.yml`
`check-vendor`	cicd	healthy	`.github/workflows/check-vendor.yml`
`find-related`	cicd	healthy	`.github/workflows/ai-issues.yml`
`update-ops-docs`	cicd	healthy	`.github/workflows/update-ops-docs.yml`
`cuda`	cicd	healthy	`.github/workflows/build-cuda-windows.yml`
`hip`	cicd	healthy	`.github/workflows/build-cuda-windows.yml`
`linux`	cicd	healthy	`.github/workflows/build-cmake-pkg.yml`
`build`	cicd	healthy	`.github/workflows/ui-build.yml`
`ubuntu-24-vulkan-cache`	cicd	healthy	`.github/workflows/build-cache.yml`
`ubuntu-24-openvino-cache`	cicd	healthy	`.github/workflows/build-cache.yml`
`windows-2022-rocm-cache`	cicd	healthy	`.github/workflows/build-cache.yml`
`windows-2025-opencl-adreno`	cicd	healthy	`.github/workflows/build-opencl.yml`
`ubuntu-24-s390x`	cicd	healthy	`.github/workflows/build-ibm.yml`
`ubuntu-24-ppc64le`	cicd	healthy	`.github/workflows/build-ibm.yml`
`gpu-cuda`	cicd	healthy	`.github/workflows/build-self-hosted.yml`
`gpu-vulkan-nvidia-cm`	cicd	healthy	`.github/workflows/build-self-hosted.yml`
`gpu-vulkan-nvidia-cm2`	cicd	healthy	`.github/workflows/build-self-hosted.yml`
`gpu-webgpu-nvidia`	cicd	healthy	`.github/workflows/build-self-hosted.yml`
`gpu-metal`	cicd	healthy	`.github/workflows/build-self-hosted.yml`
`gpu-webgpu-apple`	cicd	healthy	`.github/workflows/build-self-hosted.yml`
`gpu-vulkan-apple`	cicd	healthy	`.github/workflows/build-self-hosted.yml`
`gpu-vulkan-intel-linux`	cicd	healthy	`.github/workflows/build-self-hosted.yml`
`gpu-vulkan-intel-windows`	cicd	healthy	`.github/workflows/build-self-hosted.yml`
`gpu-openvino-low-perf`	cicd	healthy	`.github/workflows/build-self-hosted.yml`
`cpu-x64-high-perf`	cicd	healthy	`.github/workflows/build-self-hosted.yml`
`cpu-arm64-high-perf-graviton4`	cicd	healthy	`.github/workflows/build-self-hosted.yml`
`cpu-arm64-graviton4-kleidiai`	cicd	healthy	`.github/workflows/build-self-hosted.yml`
`build`	cicd	healthy	`.github/workflows/ui-build-self-hosted.yml`
`python-check-requirements`	cicd	healthy	`.github/workflows/python-check-requirements.yml`
`ctest`	cicd	healthy	`.github/workflows/build-sanitize.yml`
`create_tag`	cicd	healthy	`.github/workflows/docker.yml`
`prepare_matrices`	cicd	healthy	`.github/workflows/docker.yml`
`push_to_registry`	cicd	healthy	`.github/workflows/docker.yml`
`merge_arch_tags`	cicd	healthy	`.github/workflows/docker.yml`
`python-type-check`	cicd	healthy	`.github/workflows/python-type-check.yml`
`copilot-setup-steps`	cicd	healthy	`.github/workflows/copilot-setup-steps.yml`
`model-naming`	cicd	healthy	`.github/workflows/code-style.yml`
`ubuntu-22-hip-quality-check`	cicd	healthy	`.github/workflows/hip-quality-check.yml`
`cuda`	cicd	healthy	`.github/workflows/build-cuda-ubuntu.yml`
`hip`	cicd	healthy	`.github/workflows/build-cuda-ubuntu.yml`
`musa`	cicd	healthy	`.github/workflows/build-cuda-ubuntu.yml`
`android-ndk-snapdragon`	cicd	healthy	`.github/workflows/build-and-test-snapdragon.yml`
`linux-iot-snapdragon`	cicd	healthy	`.github/workflows/build-and-test-snapdragon.yml`

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

Label	Layer	Status	Path
`gha::build-msys`	cicd	healthy	`.github/workflows/build-msys.yml`
`gha::build-android`	cicd	healthy	`.github/workflows/build-android.yml`
`gha::build-openvino`	cicd	healthy	`.github/workflows/build-openvino.yml`
`gha::build-rpc`	cicd	healthy	`.github/workflows/build-rpc.yml`
`gha::pre-tokenizer-hashes`	cicd	healthy	`.github/workflows/pre-tokenizer-hashes.yml`
`gha::build-3rd-party`	cicd	healthy	`.github/workflows/build-3rd-party.yml`
`gha::check-vendor`	cicd	healthy	`.github/workflows/check-vendor.yml`
`gha::ai-issues`	cicd	healthy	`.github/workflows/ai-issues.yml`
`gha::update-ops-docs`	cicd	healthy	`.github/workflows/update-ops-docs.yml`
`gha::build-cuda-windows`	cicd	healthy	`.github/workflows/build-cuda-windows.yml`
`gha::build-cmake-pkg`	cicd	healthy	`.github/workflows/build-cmake-pkg.yml`
`gha::ui-build`	cicd	healthy	`.github/workflows/ui-build.yml`
`gha::build-cache`	cicd	healthy	`.github/workflows/build-cache.yml`
`gha::build-opencl`	cicd	healthy	`.github/workflows/build-opencl.yml`
`gha::build-ibm`	cicd	healthy	`.github/workflows/build-ibm.yml`
`gha::build-self-hosted`	cicd	healthy	`.github/workflows/build-self-hosted.yml`
`gha::ui-build-self-hosted`	cicd	healthy	`.github/workflows/ui-build-self-hosted.yml`
`gha::build-cann`	cicd	healthy	`.github/workflows/build-cann.yml`
`gha::python-check-requirements`	cicd	healthy	`.github/workflows/python-check-requirements.yml`
`gha::build-sanitize`	cicd	healthy	`.github/workflows/build-sanitize.yml`
`gha::docker`	cicd	healthy	`.github/workflows/docker.yml`
`gha::python-type-check`	cicd	healthy	`.github/workflows/python-type-check.yml`
`gha::copilot-setup-steps`	cicd	healthy	`.github/workflows/copilot-setup-steps.yml`
`gha::code-style`	cicd	healthy	`.github/workflows/code-style.yml`
`gha::hip-quality-check`	cicd	healthy	`.github/workflows/hip-quality-check.yml`
`gha::build-cuda-ubuntu`	cicd	healthy	`.github/workflows/build-cuda-ubuntu.yml`
`gha::build-and-test-snapdragon`	cicd	healthy	`.github/workflows/build-and-test-snapdragon.yml`
`gha::build-riscv`	cicd	healthy	`.github/workflows/build-riscv.yml`
`gha::build-vulkan`	cicd	healthy	`.github/workflows/build-vulkan.yml`
`gha::labeler`	cicd	healthy	`.github/workflows/labeler.yml`
`gha::gguf-publish`	cicd	healthy	`.github/workflows/gguf-publish.yml`
`gha::winget`	cicd	healthy	`.github/workflows/winget.yml`
`gha::close-issue`	cicd	healthy	`.github/workflows/close-issue.yml`
`gha::server-self-hosted`	cicd	healthy	`.github/workflows/server-self-hosted.yml`
`gha::build-apple`	cicd	healthy	`.github/workflows/build-apple.yml`
`gha::build-cross`	cicd	healthy	`.github/workflows/build-cross.yml`
`gha::release`	cicd	healthy	`.github/workflows/release.yml`
`gha::editorconfig`	cicd	healthy	`.github/workflows/editorconfig.yml`
`gha::build-virtgpu`	cicd	healthy	`.github/workflows/build-virtgpu.yml`
`gha::build-cpu`	cicd	healthy	`.github/workflows/build-cpu.yml`
`gha::python-lint`	cicd	healthy	`.github/workflows/python-lint.yml`
`gha::ui-self-hosted`	cicd	healthy	`.github/workflows/ui-self-hosted.yml`
`gha::server-sanitize`	cicd	healthy	`.github/workflows/server-sanitize.yml`
`gha::server`	cicd	healthy	`.github/workflows/server.yml`
`gha::build-sycl`	cicd	healthy	`.github/workflows/build-sycl.yml`
`gha::ui-publish`	cicd	healthy	`.github/workflows/ui-publish.yml`
`gha::ui`	cicd	healthy	`.github/workflows/ui.yml`
`gha::build-webgpu`	cicd	healthy	`.github/workflows/build-webgpu.yml`

Label	Layer	Status	Path
`OPENVINO_VERSION_FULL`	cicd	healthy	`—`
`ONEAPI_INSTALLER_VERSION`	cicd	healthy	`—`
`LEVEL_ZERO_SDK_URL`	cicd	healthy	`—`
`SPACEMIT_IME_TOOLCHAIN_VERSION`	cicd	healthy	`—`
`HIPSDK_INSTALLER_VERSION`	cicd	healthy	`—`
`HF_TOKEN_UI_STATIC_OUTPUT`	cicd	healthy	`—`
`CMAKE_ARGS`	cicd	healthy	`—`
`WINGET_GITHUB_TOKEN`	cicd	healthy	`—`
`QDC_API_KEY`	cicd	healthy	`—`
`PATH`	cicd	healthy	`—`
`PYPI_API_TOKEN`	cicd	healthy	`—`
`ONEAPI_ROOT`	cicd	healthy	`—`
`NDK_VERSION`	cicd	healthy	`—`
`HF_BUCKET_NAME`	cicd	healthy	`—`
`CUDA_PATH`	cicd	healthy	`—`
`GITHUB_TOKEN`	cicd	healthy	`—`
`VULKAN_SDK_VERSION`	cicd	healthy	`—`
`ROCM_VERSION_SHORT`	cicd	healthy	`—`
`OPENVINO_VERSION_MAJOR`	cicd	healthy	`—`

Label	Layer	Status	Path
`8.8.8.8`	network	healthy	`scripts/server-test-function-call.py`
`127.0.0.1`	network	healthy	`scripts/server-bench.py`
`192.168.1.1`	network	healthy	`tools/ui/src/lib/utils/url.ts`
`1.4.313.2`	network	healthy	`.github/workflows/release.yml`
`11.7.4.6`	network	healthy	`.github/actions/windows-setup-cuda/action.yml`
`12.4.5.8`	network	healthy	`.github/actions/windows-setup-cuda/action.yml`
`13.2.0.9`	network	healthy	`.github/actions/windows-setup-cuda/action.yml`
`13.5.1.27`	network	healthy	`.github/actions/windows-setup-cuda/action.yml`
`13.3.3.3`	network	healthy	`.github/actions/windows-setup-cuda/action.yml`

Label	Layer	Status	Path
`port:8080`	network	healthy	`scripts/serve-static.js`
`port:8033`	network	healthy	`examples/llama-eval/test-simulator.sh`
`port:8181`	network	healthy	`tools/ui/playwright.config.ts`
`port:256`	network	healthy	`.github/workflows/build-cross.yml`
`port:653`	network	healthy	`.github/workflows/build-cross.yml`

Label	Layer	Status	Path
`password_literal::scripts/apple/validate-tvos.sh`	security	healthy	`scripts/apple/validate-tvos.sh`
`password_literal::scripts/apple/validate-macos.sh`	security	healthy	`scripts/apple/validate-macos.sh`
`password_literal::scripts/apple/validate-ios.sh`	security	healthy	`scripts/apple/validate-ios.sh`
`password_literal::scripts/apple/validate-visionos.sh`	security	healthy	`scripts/apple/validate-visionos.sh`
`generic_api_key::tools/server/tests/unit/test_security.py`	security	healthy	`tools/server/tests/unit/test_security.py`

Label	Layer	Status	Path
`sqlite`	data	healthy	`scripts/compare-llama-bench.py`
`redis`	data	healthy	`scripts/server-test-parallel-tc.py`
`postgresql`	data	healthy	`tools/ui/tests/stories/fixtures/ai-tutorial.ts`

Label	Layer	Status	Path
`legacy-migration.ts`	data	healthy	`tools/ui/src/lib/utils/legacy-migration.ts`
`migration.service.ts`	data	healthy	`tools/ui/src/lib/services/migration.service.ts`

Label	Layer	Status	Path
`repobility-clone-x05gx6ke`	software	healthy	`/tmp/repobility-clone-x05gx6ke`

Label	Layer	Status	Path
`rabbitmq`	data	healthy	`scripts/server-test-parallel-tc.py`

Label	Layer	Status	Path
`server_bench`	data	healthy	`scripts/server-bench.py`

Label	Layer	Status	Path
`nginx`	network	healthy	`tools/ui/src/lib/utils/syntax-highlight-language.ts`

Label	Layer	Status	Path
`gpu (detected)`	hardware	healthy	`scripts/create_ops_docs.py`

Label	Layer	Status	Path
`auth::scripts/server-test-parallel-tc.py`	security	healthy	`scripts/server-test-parallel-tc.py`

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/66068b6a-6304-4731-a390-59c7a48d3b50/

To check status programmatically (no auth required):

curl -s https://repobility.com/api/v1/public/scan/66068b6a-6304-4731-a390-59c7a48d3b50/

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.

ggml-org/llama.cpp

Complete repo analysis

function 50+

file 50+

class 50+

directory 50+

job 50+

pipeline 48

env_var 19

service 9

port 5

secret 5

database 3

migration 2

repo 1

queue 1

table 1

load_balancer 1

gpu 1

auth 1