design-review
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill acts as a process manual for architectural review. It guides the agent to trace code execution paths, identify invariants, and suggest minimal, scoped changes based on repository-specific documentation. No high-risk command execution or data exfiltration patterns were detected.
- [NO_CODE]: The skill consists exclusively of markdown instructions (SKILL.md) and relative links to internal documentation. There are no associated scripts, binaries, or configuration files that execute logic at the system level.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external data such as source code diffs and design proposals. While this constitutes an ingestion point for potentially untrusted data, the instructions mitigate risk by directing the agent to maintain the user's scope, technology choices, and a read-only status for review-only requests.
Audit Metadata