grill-me
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional text for a specific agent persona. It does not include any executable code, network exfiltration, or attempts to access sensitive system files.
- [INDIRECT_PROMPT_INJECTION]: The skill uses a standard ingestion surface by reading user-supplied plans and exploring the codebase. 1. Ingestion points: User plans and codebase content (SKILL.md). 2. Boundary markers: None present to delimit external data. 3. Capability inventory: Reading codebase files. 4. Sanitization: No sanitization is performed on ingested data.
Audit Metadata