docs-keeper
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFE
Full Analysis
- [Indirect Prompt Injection] (SAFE): The skill processes existing project documentation, creating a surface for indirect prompt injection, though the risk is minimal given its intended use.\n
- Ingestion points: The skill reads
README.md,docs/*.md, anddocs/agents/PLAN.mdto gather project context.\n - Boundary markers: The skill encourages logical separation between 'Human' and 'Agent' zones, but does not provide specific technical delimiters for ingested content.\n
- Capability inventory: The agent can create directories, create/modify files within the project repository, and execute the
lncommand for symlinking.\n - Sanitization: No sanitization or validation of the documentation content is performed before processing.
Audit Metadata