roborev-refine-and-polish
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a procedural methodology for tracking AI-driven code reviews. It contains instructions for the agent to follow rather than automated scripts.- [COMMAND_EXECUTION]: The skill utilizes the roborev CLI to perform reviews and manage job logs. These interactions are consistent with the skill's documented purpose.- [DATA_EXFILTRATION]: The skill includes strong privacy guidelines, instructing the agent to use private directories for logs and to avoid exposing these logs in public commit messages or pull requests.- [PROMPT_INJECTION]: While the skill involves processing output from other AI agents (an indirect prompt injection surface), it mandates manual distillation and verification of findings, which acts as a reasoning filter to prevent accidental execution of embedded instructions.- [EXTERNAL_DOWNLOADS]: The skill references the official roborev.io website for tool documentation and setup. These references are legitimate and contextually appropriate.
Audit Metadata