linkup-extract

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

• Third-party content exposure detected (low risk: 0.10). Skill.md describes POST /v1/extract (and async GET /v1/extract/{id} then downloading resultUrl) as turning a provided url plus free-text q into extracted records from the specified webpage content, meaning outsider-authored page text is ingested whenever the caller supplies a URL whose content is attacker-controlled.