afrexai-lead-hunter

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

• Third-party content exposure detected (high risk: 0.90). The skill's required Discovery and Enrichment workflows (Phase 2 and Phase 3 in SKILL.md) explicitly instruct the agent to run web_search and visit public third‑party sources—LinkedIn, company websites, GitHub, Crunchbase, Product Hunt, job boards, G2/Clutch reviews, podcast transcripts, etc.—and to read/interpret user-generated content which is then used to score leads and autonomously trigger outreach (Phase 8 Autopilot), creating a clear vector for indirect prompt injection.