dev-review
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No malicious patterns or behaviors detected. The skill uses standard local development tools including Bash (limited to git diff and git log), Read, Grep, and Glob to perform its primary function of reviewing source code changes.
- [Prompt Injection] (SAFE): An indirect prompt injection surface is present because the skill ingests untrusted source code and git diffs. Evidence Chain: 1. Ingestion points: Phase 1 involves reading local files and git diff output. 2. Boundary markers: Absent; there are no specific instructions to ignore agent commands embedded in the code being reviewed. 3. Capability inventory: The skill utilizes Bash, Read, Grep, and Glob for analysis. 4. Sanitization: Absent; code is read as-is. This surface is considered safe given the skill's specific purpose and limited toolset.
Audit Metadata