tam-builder

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests third‑party data from Apollo Company Search/People Search and optional SixtyFour enrichment (see SKILL.md and scripts/tam_builder.py / enrich_companies / build_watchlist), and the agent reads and acts on that untrusted external content to compute scores, assign tiers, build watchlists, and decide database writes/enrichments—so external content can materially influence actions.