grill-me
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns detected. The skill consists entirely of natural language instructions to guide an AI agent's behavior during a design review or planning session. There are no command executions, network requests, or credential handling operations within the skill itself.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to explore the codebase to answer questions, which creates a surface for indirect prompt injection if the codebase contains malicious instructions. However, this is an inherent risk of codebase analysis tools and is consistent with the skill's primary purpose. 1. Ingestion points: The skill accesses the user's codebase (SKILL.md). 2. Boundary markers: None. 3. Capability inventory: The agent uses its built-in codebase exploration tools. 4. Sanitization: None.
Audit Metadata