review-architecture-scope

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown-based instructions for an AI agent to perform code reviews. It does not include any executable scripts, tool definitions, or network capabilities.\n- [DATA_EXPOSURE]: The instructions specifically direct the agent to check for the exposure of secrets, credentials, and personal data (P0 findings), which is a defensive security feature rather than a vulnerability.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code and instructions as part of its review process. However, the risk is minimal because the skill has no tool-calling capabilities and explicitly instructs the agent not to modify the pull request or post comments.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 03:39 PM
Security Audit — agent-trust-hub — review-architecture-scope