worktree

Warn

Audited by Snyk on May 20, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill calls the GitHub CLI (gh pr list --head --state all --json number,state,mergedAt) in both status and cleanup steps to read PR metadata from GitHub (user-generated, third-party content) and uses that PR state to decide whether to remove worktrees/branches, so external PR data can materially influence actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 20, 2026, 06:56 AM
Issues
1
Security Audit — snyk — worktree