setup
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and provides commands for downloading language runtimes and development tools from established services, including NodeSource, Vercel (fnm), Astral (uv), and Rustup.
- [COMMAND_EXECUTION]: Extensive use of shell commands for repository inspection, environment discovery, and toolchain validation. This includes git operations (log, rev-parse, commit) and standard Unix utilities (grep, sort, uniq, cut).
- [REMOTE_CODE_EXECUTION]: The AI Code Review module generates GitHub Actions workflows designed to run CLI tools like Claude and Codex to analyze pull request diffs. These workflows are configured to run within the user's CI/CD environment upon explicit selection.
- [PROMPT_INJECTION]: The skill implements an analysis phase that reads repository content and git history to derive project-specific semantic rules. While this ingests untrusted local data, the risk is mitigated by a mandatory user review and confirmation phase before any rules are finalized or written to disk.
Audit Metadata