linkup

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

• Third-party content exposure detected (high risk: 1.00). The skill issues real-time web searches and fetches webpage content via the Linkup API (e.g., POST to https://api.linkup.so/v1/search and /v1/fetch) which retrieves arbitrary public URLs and search results from the open web that the agent is expected to read and interpret, exposing it to untrusted third-party content.