grilling
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows standard instructional patterns for persona-based interaction. No prompt injection or malicious overrides were detected.- [SAFE]: Instructions regarding environment exploration (filesystem, tools) are scoped to finding factual information to support the user's decision-making process. No evidence of unauthorized file access or data exfiltration attempts was found.- [SAFE]: The skill does not include external dependencies, remote code execution, or obfuscated content.
Audit Metadata