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 (12 hours, 15 minutes ago) · 10 languages

925 findings (233 legacy + 692 scanner) 11/13 scanners ran Scanner says 72 (higher by 6)

File as issue Image

UNIFIED Repobility · multi-layer engine · AI coders

Complete repo analysis

Last scanned 12 hours, 14 minutes ago · v2 · 579 findings from 2 sources. Findings combine the legacy security pipeline AND the multi-layer engine (atlas, wiring, flows, ranked) AND verified AI agent contributions.

JSON

100.0% cov · 346 gaps

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 9 High 151 Medium 71 Low 287 9-Layer: Software Security Quality Integrity Frontend Hardware Data Network Cicd Source: Legacy 233 9-layer 346 Crowd 0 Layer: Software 142 Quality 236 Security 20 Api 1 Frontend 19 Network 2 Cicd 159

Exclude dismissed / FP Exclude test files

Bug-class explainers. Each card groups findings of the same shape — these are the patterns most likely to ship to prod and reappear in future scans unless you systematically fix the cause, not just the instance.

Fragile runtime 173 findings

What it is: Code that runs but breaks under predictable input — division by zero, missing keys, unbounded loops, off-by-one slicing.

Why it matters: Reaches production undetected because happy-path tests pass. First user with a weird input crashes the request.

How AI causes it: AI loves writing the happy path; doesn't probe edge cases unless explicitly asked.

Fix approach: Add property-based tests. Wrap external inputs with explicit validators. Use the framework's typed deserializer (Pydantic, attrs).

12 matching findings on this repo

medium [MINED111] Bare except continues silently: Bare `except:` (or `except Exception… examples/model-conversion/scripts/utils/check-nms…:44
medium [MINED111] Bare except continues silently: Bare `except:` (or `except Exception… examples/model-conversion/scripts/utils/check-nms…:172
medium [MINED111] Bare except continues silently: Bare `except:` (or `except Exception… examples/model-conversion/scripts/utils/hf-create…:56
medium [MINED111] Bare except continues silently: Bare `except:` (or `except Exception… examples/model-conversion/scripts/utils/hf-upload…:44
medium [MINED111] Bare except continues silently: Bare `except:` (or `except Exception… examples/model-conversion/scripts/utils/semantic_…:142
medium [MINED111] Bare except continues silently: Bare `except:` (or `except Exception… examples/model-conversion/scripts/utils/hf-add-mo…:31
medium [MINED111] Bare except continues silently: Bare `except:` (or `except Exception… examples/model-conversion/scripts/utils/hf-add-mo…:49
medium [MINED111] Bare except continues silently: Bare `except:` (or `except Exception… examples/model-conversion/scripts/utils/inspect-o…:111
medium [MINED111] Bare except continues silently: Bare `except:` (or `except Exception… examples/model-conversion/scripts/utils/inspect-o…:120
medium [MINED111] Bare except continues silently: Bare `except:` (or `except Exception… examples/model-conversion/scripts/utils/inspect-o…:50
medium [MINED111] Bare except continues silently: Bare `except:` (or `except Exception… examples/model-conversion/scripts/utils/inspect-o…:218
medium [MINED111] Bare except continues silently: Bare `except:` (or `except Exception… examples/model-conversion/scripts/embedding/run-o…:127

View all fragile runtime findings →

Legacy markers 10 findings

What it is: TODO, FIXME, XXX, HACK comments. Often indicate a known-broken path the author meant to fix.

Why it matters: Each marker is an unfinished thought. Production code shouldn't ship with debt that's documented but not tracked.

How AI causes it: AI mirrors the style of the codebase, so existing TODOs propagate into new code.

Fix approach: Convert each into a ticket. Delete the comment when the ticket lands. Use a pre-commit hook to block new TODOs without an issue link.

10 matching findings on this repo

low Stray `console.log` in TS/JS — tools/ui/src/lib/utils/legacy-migration.ts:337
low Very large file: examples/convert_legacy_llama.py (1463 lines)
low Legacy-named symbol `time_mix_v1` in gguf-py/gguf/constants.py:1149
low Legacy-named symbol `lazy_rebuild_tensor_v2` in examples/convert_legacy_llama.p…
info Commented-code block (6 lines) in examples/convert_legacy_llama.py:557
info Commented-code block (6 lines) in tools/mtmd/legacy-models/minicpmv-convert-ima…
low Legacy-named symbol `is_unused` in conversion/chatglm.py:62
low Legacy-named symbol `gptq_v2` in conversion/base.py:378
low Legacy-named symbol `G0_v1` in conversion/qwen.py:363
low Legacy-named symbol `time_mix_v1` in conversion/rwkv.py:246

View all legacy markers findings →

Commented-out code 21 findings

What it is: Lines of source that were intentionally disabled but never deleted.

Why it matters: Git already remembers history — commented code rots, becomes wrong, and adds noise to diffs.

How AI causes it: AI sometimes comments out broken code instead of fixing it. Reviewers approve out of inertia.

Fix approach: Delete. Trust `git log`. If you really need to remember, save it in a notes file under `docs/`.

12 matching findings on this repo

info Commented-code block (16 lines) in tests/test-tokenizer-0.py:27
info Commented-code block (5 lines) in tests/test-tokenizer-random.py:502
info Commented-code block (10 lines) in scripts/tool_bench.py:24
info Commented-code block (7 lines) in gguf-py/tests/test_quants.py:46
info Commented-code block (6 lines) in gguf-py/gguf/gguf_reader.py:75
info Commented-code block (6 lines) in examples/convert_legacy_llama.py:557
info Commented-code block (6 lines) in tools/ui/src/app.d.ts:62
info Commented-code block (7 lines) in tools/ui/src/lib/constants/settings-registry.…
info Commented-code block (6 lines) in tools/ui/src/lib/services/mcp.service.ts:563
info Commented-code block (6 lines) in tools/mtmd/legacy-models/minicpmv-convert-ima…
info Commented-code block (18 lines) in tools/server/tests/unit/test_tool_call.py:132
info Commented-code block (13 lines) in conversion/deci.py:41

View all commented-out code findings →

Config drift 7 findings

What it is: Settings duplicated across env files, Docker compose, K8s, and code defaults, all with slightly different values.

Why it matters: Production behaviour depends on whichever copy your loader reads first. Subtle bugs in staging that don't reproduce in dev.

How AI causes it: AI writes new config from memory rather than reading the existing source.

Fix approach: Pick one source of truth (env vars + a settings module). Have every other place import from there. Lint for duplicates in CI.

7 matching findings on this repo

high [MINED131] pre-commit hook `https://github.com/PyCQA/flake8` pinned to mutable … .pre-commit-config.yaml:12
high [MINED131] pre-commit hook `https://github.com/pre-commit/pre-commit-hooks` pin… .pre-commit-config.yaml:5
low File has no detected symbols: tools/ui/playwright.config.ts
low File has no detected symbols: tools/ui/vite.config.ts
low File has no detected symbols: tools/ui/svelte.config.js
low File has no detected symbols: tools/ui/eslint.config.js
low 16 env vars used in code but missing from .env.example

View all config drift findings →

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.