skills/marcioaltoe/skills/roundfix/Gen Agent Trust Hub

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 roundfix and rtk (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
Risk Level
SAFE
Analyzed
Jun 17, 2026, 07:27 PM
Security Audit — agent-trust-hub — roundfix