grill-me
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions include codebase exploration to resolve questions, which introduces an indirect prompt injection surface where content in codebase files could influence agent behavior. This is handled as safe because it is the primary intended functionality.
- Ingestion points: Local codebase files (SKILL.md)
- Boundary markers: Absent
- Capability inventory: File system exploration and reading (SKILL.md)
- Sanitization: Absent
- [SAFE]: No findings related to data exfiltration, obfuscation, persistence, or malicious command execution were detected during the analysis of the skill metadata and body.
Audit Metadata