pr-review
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from GitHub Pull Request titles, descriptions, and code diffs from the toss/es-toolkit repository. This external content enters the agent context without sanitization or explicit boundary markers. 1. Ingestion points: PR metadata and source diffs. 2. Boundary markers: None. 3. Capability inventory: gh, yarn, and tsc commands. 4. Sanitization: None.
- [COMMAND_EXECUTION]: The workflow uses the gh CLI to list PRs and executes yarn vitest and tsc --noEmit for local validation, representing standard operations within the skill's purpose.
Audit Metadata