grill-me
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to answer questions by exploring the codebase, creating an attack surface for indirect prompt injection from file content.\n
- Ingestion points: Codebase files (referenced in SKILL.md).\n
- Boundary markers: No markers or 'ignore' instructions are used when reading codebase data.\n
- Capability inventory: The agent is permitted to read codebase files.\n
- Sanitization: No content validation or sanitization is described.\n- [NO_CODE]: This skill consists exclusively of markdown-based instructions and does not provide any scripts, binaries, or configuration files.
Audit Metadata