cv-data-ingestion

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md processing workflow (Phase 2: "Link Extraction" and "Link validation") explicitly instructs extracting and verifying external URLs from company websites, LinkedIn, GitHub, product docs and press pages and to use those live third‑party pages as primary enrichment/validation, so the agent will fetch and interpret untrusted public web content that can materially influence its outputs.