grill-me
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, data exfiltration, or unauthorized command execution detected in the skill logic or metadata.
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface Analysis:
- Ingestion points: The skill processes user-provided plans, designs, and architectures as described in
SKILL.md(Step 0). - Boundary markers: No explicit delimiters or 'ignore embedded instructions' warnings are defined for the plan content.
- Capability inventory: The skill utilizes file system read access to explore relevant codebases if available.
- Sanitization: The skill does not perform explicit sanitization or validation of the processed user data.
Audit Metadata