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 Phase 1 and Workflows/EntityLookup.md Phase 2/7 and PeopleTools.md) explicitly instruct researcher agents and tools (PerplexityResearcher, URLScan.io, crt.sh, social media, paste sites, Telegram/Discord, search engine discovery, etc.) to fetch and ingest public, user-generated web and social content which is then used as gating/decision criteria (blocking domain-discovery quality gates and follow-up actions), exposing the agent to untrusted third‑party content that could carry indirect prompt injection.