source-verification

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 analyze untrusted public web content—e.g., reverse image searches and social-media account analysis using Google Images, TinEye, Yandex, YouTube DataViewer, and archiving URLs via web.archive.org/save—which the agent is expected to read and use to drive verification decisions.