lead-intelligence

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly fetches and ingests public third‑party content (Exa web search, X API, LinkedIn via browser control, GitHub and general web fetch) as required in the SKILL.md and agent docs (enrichment-agent, signal-scorer, mutual-mapper), and that untrusted user-generated content is read and directly used to score targets, choose channels, and craft outreach—allowing third‑party content to materially influence agent decisions.