skills/lennney/skills/grilling/Gen Agent Trust Hub

grilling

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of natural language instructions guiding the agent's behavior during a design review. No malicious patterns, prompt injections, or obfuscation techniques were found.
  • [COMMAND_EXECUTION]: The instructions direct the agent to "explore the codebase" to answer questions. This relies on the agent's existing file system tools and is consistent with the skill's stated purpose of stress-testing plans and designs within a development context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 02:27 PM
Security Audit — agent-trust-hub — grilling