audit-docs
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content by reading project-specific documentation, roadmaps, and fix indexes.
- Ingestion points: Files such as
roadmap.md,fix-index.md, and various feature documentation files (PLAN.md,TASKS.md,progress.md) are read to audit project consistency. - Boundary markers: The instructions do not specify explicit delimiters or warnings to the agent for ignoring instructions that might be embedded in the audited documentation.
- Capability inventory: The skill uses
grepfor searching, performs file reads and writes (when the--fixflag is used), and executes GitHub CLI (gh) commands to verify pull requests and issues. - Sanitization: No explicit sanitization or filtering of the content read from files is mentioned before the agent processes it in its context.
Audit Metadata