linkup-fetch

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

• Third-party content exposure detected (high risk: 0.95). The required runtime workflow for this skill is to call Linkup Fetch on a user-supplied URL, which returns the fetched page’s outsider-authored web content as clean Markdown that is then fed into the agent’s LLM context (Search+Fetch→LLM pattern).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill makes runtime calls to Linkup's APIs (notably https://api.linkup.so/v1/fetch) to retrieve arbitrary web page content which is then fed into LLM prompts, so external content can directly control agent instructions.