refactor-ci-agent
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill promotes security-first configurations by providing 'Before vs After' examples that demonstrate how to avoid credential leakage and mitigate supply chain risks through action pinning.
- [COMMAND_EXECUTION]: The skill documents the execution of a CI pipeline that runs diagnostic scripts (
diagnose.mjs,guidelines.mjs,orchestrate.mjs) and an optional, user-defined agent command (agent-cmd). The documentation explicitly warns against including credentials in the command string. - [EXTERNAL_DOWNLOADS]: The skill references standard GitHub Actions, including
actions/checkoutandactions/setup-node, as well as the vendor's own composite action for generating reports. - [SAFE]: No malicious patterns, prompt injections, or obfuscated code segments were detected. The included utility script (
scripts/checklist.mjs) is benign and used only for formatting internal checklists.
Audit Metadata