how
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves reading and analyzing files from the user's codebase using tools like Glob, Grep, and Read. This creates an attack surface where malicious instructions embedded in the code (e.g., in comments or documentation) could potentially influence the subagents' behavior during the exploration or critique phases.
Audit Metadata