vector-db-audit — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited vector-db-audit (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
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.
Systematically audits the Vector Database to identify gaps between the project manifest and the actual document chunks stored in ChromaDB.
Run the audit for a specific profile (e.g., wiki) to generate a coverage report and a CSV of gaps:
python scripts/audit_vector.py --profile wiki --report vector_audit.txt --csv missing_vector.csvmissing_vector.csv.vector-db-ingest --profile wiki --file [path] to fill specific gaps.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.