grill-me
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to answer questions by exploring the user's codebase, which creates a surface where malicious instructions embedded in codebase files could influence the agent's behavior during the interview process.\n
- Ingestion points: Local codebase files (referenced in SKILL.md).\n
- Boundary markers: Absent; no delimiters or instructions to ignore embedded commands within codebase files are provided.\n
- Capability inventory: The agent is permitted to read and analyze workspace files.\n
- Sanitization: Absent; the skill does not provide mechanisms to filter or validate content retrieved from the codebase.
Audit Metadata