OSINT

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflows (e.g., Workflows/CompanyDueDiligence.md, CompanyLookup.md, EntityLookup.md, PeopleLookup.md and associated tools files) explicitly instruct agents to fetch and ingest public web content and user-generated sources — crt.sh, search engines, social media, paste sites, VirusTotal/URLScan, forums/Telegram/Discord, etc. — and to use those findings to drive blocking quality gates, agent tasks, and decision-making, which creates a clear pathway for indirect prompt injection from untrusted third‑party content.