grill-me
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, unauthorized command execution, or hidden data exfiltration attempts were identified. The skill consists of instructional markdown guiding a workflow.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data such as repository facts, tickets, and pull requests. While this creates a potential surface for indirect prompt injection, it is the intended primary purpose of the skill. The instructions emphasize verifying facts through research and obtaining user confirmation for all decisions, which acts as a mitigating control.
Audit Metadata