contactout

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and enrich LinkedIn profiles and public domain/company pages (e.g., /v1/linkedin/enrich and /v1/people/linkedin endpoints), which are untrusted, user-generated public web content that the agent ingests and can materially influence its actions.