grill-me
Pass
Audited by Gen Agent Trust Hub on Oct 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 creates an attack surface where untrusted content in files could influence the agent's behavior. \n- Ingestion points: The agent reads content from the local codebase as specified in SKILL.md. \n- Boundary markers: There are no boundary markers or instructions to ignore embedded instructions in the ingested data. \n- Capability inventory: The skill allows codebase exploration and file reading. \n- Sanitization: There is no evidence of sanitization or filtering of the ingested content.
Audit Metadata