nutmeg-heal

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to fetch and inspect third‑party web pages and API responses during diagnosis ("For web scrapers: fetch the page and compare HTML structure..." and "For APIs: make a minimal test request..."), so it ingests untrusted public content that can directly influence debugging actions.