roundfix
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a security-first approach by explicitly instructing the agent to treat all reviewer text as untrusted input and forbidding the execution of commands found in review bodies unless independently justified.
- [SAFE]: The skill's primary operations involve standard command-line interactions with the
roundfixandrtk(Roundfix ToolKit) utilities, which are consistent with the tool's stated purpose of PR cleanup. - [SAFE]: No obfuscated code, unauthorized data exfiltration patterns, or suspicious remote dependencies were identified. The external services involved (GitHub and CodeRabbit) are standard platforms for the skill's intended use case.
Audit Metadata