grilling
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to explore the codebase to answer questions, which introduces untrusted data into the context.
- Ingestion points: Local codebase files (SKILL.md).
- Boundary markers: Absent.
- Capability inventory: File system read access (implied).
- Sanitization: Absent.
Audit Metadata