git-worktree
Warn
Audited by Snyk on Feb 16, 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's scripts (scripts/clone_repo.sh and scripts/create_worktree.sh) accept arbitrary repository URLs and run git clone / git fetch against public repositories (e.g., GitHub), therefore the agent will ingest untrusted, user-hosted code/content from third‑party sites as part of its workflow.
Audit Metadata