rlm-worktree

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (Worktree Creation Process Step 4 "Run Project Setup" with commands like npm install, pip install, cargo build, go mod download, mvn/gradle tasks) fetches and executes dependencies from public package registries and Step 5 "Verify Clean Test Baseline" runs tests and records their outputs, meaning untrusted third‑party content is ingested and interpreted as part of decision-making.