healthcare-providers-extract

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and ingests open web content (practice websites, Google Maps listings, Yelp/BBB listings) via nimble extract/search and WSA discovery (see SKILL.md Step 2b "Extract from listing page" and Step 3/4 with nimble extract --url plus references/wsa-reference.md listing Google Maps/Yelp/BBB), and that untrusted third‑party content is parsed and used to drive extraction, deduplication, confidence scoring, and follow-up actions — creating a clear vector for indirect prompt injection.