code-review
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and evaluate external codebases, modules, and pull requests. This data is untrusted and could contain hidden instructions (e.g., in comments or documentation) meant to override the agent's constraints. * Ingestion points: Codebase files, git history logs, and diff outputs. * Boundary markers: None present to distinguish instructions from analyzed data. * Capability inventory: Executes git commands and npm scripts (test, build, lint). * Sanitization: No sanitization or validation of the input code is performed before processing.
- [COMMAND_EXECUTION]: The skill performs shell command execution via git (log, diff) and npm (run typecheck, run lint, run test, run build, audit). These commands interact with local project configuration and execute logic defined in the target codebase's package.json.
Audit Metadata