prospect-research-to-cadence

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

• Third-party content exposure detected (high risk: 0.90). The skill's Stage 1 research explicitly ingests public third‑party content — e.g., "Web search" for recent news, "apollo_organizations_job_postings", and Clay's waterfall enrichment (aggregating 50+ external data providers and social profiles) — and then uses those untrusted signals as personalization triggers that directly shape email/call drafts and sequence loading (see SKILL.md Stage 1 and reference/email-templates.md), so external content can materially influence agent actions.