grill-me
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an interactive loop where the agent processes user-provided answers to recompute a 'design tree' and determine future actions. This is a standard interactive surface for conversational agents. The instructions include a proactive security measure by requiring the agent to present a final summary of all decisions and wait for explicit user confirmation before performing any write operations, such as editing files or creating pull requests.
Audit Metadata