create-pr

Warn

Audited by Snyk on Feb 25, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md Step 1 explicitly instructs using gh issue list and gh issue view to find and read GitHub issues (public, user-generated content) which the agent must interpret to decide which issues to link/close and to shape PR content, so untrusted third-party content can materially influence behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 25, 2026, 11:31 AM