doc-writing — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited doc-writing (Agent Skill) and scored it 45/100 (orange). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 1 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Generate structured API documentation from a route manifest.
You will receive a route manifest (JSON array) from the previous pipeline stage. Each entry contains: method, path, file, line, middleware, type.
For each route in the manifest, read the source file to understand:
Use the template at templates/endpoint-doc.md for each route group.
Group routes by their source file (e.g., all product routes together).
Write one markdown file per route group to the docs/ directory:
docs/products-api.mddocs/categories-api.mdReturn a manifest of generated documentation files:
{
"files_generated": ["docs/products-api.md", "docs/categories-api.md"],
"routes_documented": 8,
"routes_skipped": [],
"warnings": []
}This manifest will be consumed by the next pipeline stage (quality-checking).
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.