inbound-lead-qualification

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md (Step 3 and Step 5) instructs the agent to perform web search and scrape/read LinkedIn company pages, company websites, job postings, and other enrichment tool outputs (public third‑party content) and to use those findings to score and route leads, so untrusted external content can directly influence decisions and actions.