find-linkedin-contacts

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to fetch external company websites and job postings via Jina Reader and search LinkedIn via browser, which allows outsider-authored web content and profile pages to enter the agent's context.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to fetch external content from Jina Reader (https://r.jina.ai/), which acts as an operational dependency providing runtime processing and web content retrieval for skill execution under a third-party service provider (Jina AI).