grill-me
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to 'explore the codebase' to answer questions, which is a surface for processing untrusted data.
- Ingestion points: Files within the user's codebase (SKILL.md).
- Boundary markers: The prompt does not define delimiters or provide specific instructions to the agent to disregard potential instructions embedded within the codebase files.
- Capability inventory: The agent uses standard file system access and analysis tools to perform the exploration.
- Sanitization: No explicit sanitization or input validation logic is present to handle the external content being processed.
Audit Metadata