anysite-lead-generation

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and parse public third‑party content (e.g., LinkedIn via mcp__anysite__search_linkedin_users and mcp__anysite__get_linkedin_profile, arbitrary websites via mcp__anysite__parse_webpage and mcp__anysite__get_sitemap, and social platforms like Instagram/Y Combinator), and the agent is expected to read and interpret that untrusted, user-generated content as part of its workflows, creating exposure to indirect prompt injection.