heal

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent in the "Diagnosis process" to fetch web pages ("For web scrapers: fetch the page and compare HTML structure") and make test API requests, which means the agent will read and act on untrusted public web/API content that can influence its debugging actions.