skills/a-canary/arc-skills/grilling/Gen Agent Trust Hub

grilling

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains no executable code, network operations, or sensitive file access. The instructions are focused on guiding the agent's conversational behavior to perform a thorough design review.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to explore the codebase for facts. While this involves reading external data, the skill includes a strong boundary by requiring explicit user confirmation before any actions ("enacting the plan") are taken, and it focuses on interviewing the user rather than automated execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 07:47 PM
Security Audit — agent-trust-hub — grilling