librarian

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly uses grep_app and opensrc.fetch to retrieve and read content from public third‑party sources (e.g., GitHub repositories and packages from npm/PyPI/crates) and instructs the agent to read README, package.json, and source files, meaning the agent will consume untrusted user-generated content that could carry indirect prompt injection.