create-production-pr

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) to perform repository operations such as branch verification, commit comparison, and PR creation. These are legitimate operations intended for development automation.
  • [PROMPT_INJECTION]: The skill processes untrusted data from existing Pull Request titles and bodies, which presents a surface for indirect prompt injection.
  • Ingestion points: Pull Request titles and bodies retrieved via gh api and gh pr view in SKILL.md (Steps 4 and 5).
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are used when interpolating this content into the new PR body.
  • Capability inventory: The skill's capabilities are limited to creating new Pull Requests via gh pr create in SKILL.md (Step 9).
  • Sanitization: No explicit sanitization of the retrieved content is performed before it is added to the new PR description.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 02:15 PM
Security Audit — agent-trust-hub — create-production-pr