linkup

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

• Third-party content exposure detected (high risk: 1.00). This skill clearly fetches and ingests untrusted public web content via its /search and /fetch endpoints (SKILL.md: "The /search endpoint allows you to retrieve web content" and "The /fetch endpoint allows you to fetch a single webpage from a given URL"), so third‑party pages could inject instructions that influence agent behavior.