lead-research-assistant

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to fetch and analyze publicly available, user-generated content from third-party sites such as LinkedIn, GitHub, Twitter/X, Crunchbase, Product Hunt and company websites, so the agent would read untrusted external content as part of its workflow.