style-reviewer
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is strictly limited to reviewing code style, naming conventions, and formatting consistency based on local configuration files like .eslintrc and pyproject.toml.
- [SAFE]: There are no signs of prompt injection, data exfiltration, or obfuscation. The skill explicitly instructs the agent to 'stay in lane' and avoid security or logic audits while performing style reviews.
- [SAFE]: Tooling guidance encourages using existing project-local scripts and standard formatters (e.g., Prettier, Ruff, Gofmt) rather than executing arbitrary or untrusted commands.
- [SAFE]: While the skill ingests untrusted code for review (an indirect prompt injection surface), this is central to its primary purpose and is handled through passive analysis without evidence of unsafe interpolation or automated execution of the processed code.
Audit Metadata