rule
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from multiple sources to influence its logic and modify project files.
- Ingestion points: Reads from
AGENTS.md,CLAUDE.md, various editor rule folders, and takes direct user instructions/corrections. - Boundary markers: The instructions do not specify any delimiters or safety markers for the content being read from these files.
- Capability inventory: The skill possesses file-read and file-write capabilities, as well as the ability to search and modify the entire codebase ("Sweep the code") to fix rule violations.
- Sanitization: There is no evidence of sanitization, validation, or escaping of the content ingested from the external rule files or user corrections before it is used to modify the codebase.
Audit Metadata