build-tam

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests untrusted, public web content for decision-making—see the enrichment steps that call crustdata_job_listings and exa_search (website content) and the "site:domain.com" anti-fit checks in SKILL.md—which the agent then reads/keywords-scores to drive exclusions and prioritization.