ai-sdr

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to ingest and act on untrusted public third‑party content—see Section 2 (Day 8-9 "AI Personalization Layer" which uses recent LinkedIn posts and company news) and references/implementation-guide.md (Signal Source Stack listing Clay signals, LinkedIn activity, news/PR monitoring, BuiltWith, web scraping via Claygent)—and that external content is used to drive personalization, sequencing, and routing decisions.