skills/open-mercato/skills/review-prs/Gen Agent Trust Hub

review-prs

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Uses the GitHub CLI (gh) to list open pull requests and retrieve user information, which is appropriate for managing review queues.
  • [SAFE]: Reads project configuration from .ai/agentic.config.json and delegates complex tasks to trusted workflow skills like auto-review-pr.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting external PR data. 1. Ingestion points: PR titles and labels from gh pr list. 2. Boundary markers: None present. 3. Capability inventory: Orchestrates the auto-review-pr skill. 4. Sanitization: Metadata is processed as-is. This behavior is standard for the skill's primary purpose and carries minimal risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 01:11 PM
Security Audit — agent-trust-hub — review-prs