grill-me
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains only instructional markdown and configuration files. It does not include any executable scripts, network operations, or requests for sensitive data.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to inspect the local project environment (files and documentation) to resolve facts. While this creates an ingestion point for untrusted data that could influence the agent's questions, the lack of dangerous capabilities (like file writing or network requests) minimizes the risk.
- Ingestion points: Project files and documentation mentioned in SKILL.md (Interview loop step 1).
- Boundary markers: Not present.
- Capability inventory: The skill does not define any scripts, subprocess calls, or network operations.
- Sanitization: Not present.
Audit Metadata