clay-to-deepline

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and interprets untrusted third-party content — e.g., extracting prompts and cell values from HAR/bulk-fetch-records and portableSchema (Phase 1 §1.5) and performing web/social searches and reads via exa_search, apify_run_actor_sync, crustdata_linkedin_posts and WebSearch (binary-search-optimizer and clay-action-mappings) — and uses those results to drive follow-up actions and AI passes, which can enable indirect prompt injection.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches Clay data at runtime from endpoints like https://api.clay.com/v3/tables/{TABLE_ID} and https://api.clay.com/v3/tables/{TABLE_ID}/bulk-fetch-records, and those responses contain rendered prompts/formulaText that the migration uses verbatim to build Deepline prompts, so the external URL directly controls agent prompts and is a required runtime dependency.