bun-test

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

• Third-party content exposure detected (high risk: 0.80). The skill's examples (PATTERNS.md "fetches from network" and the runtime query ID store tests) show fetching and parsing content from public sites like "https://x.com" and external bundle.js files, which are untrusted third‑party/user-generated web content that the agent is expected to read/interpret as part of its workflow.