company-hiring-intelligence

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to scrape and ingest content from public third‑party sites (the company careers page, LinkedIn Jobs, and the company's engineering blog) via TinyFish agents and to use that content to drive analyses and synthesis, which meets the criteria for exposure to untrusted, user-generated web content that can influence tool behavior.