product-help-center

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly requires running fresh web searches and fetching/verifying external sources (see "Trend Awareness Protocol" and "Fact-Checking" sections, plus references to data/sources.json and required searches), so the agent will ingest and act on open/public third‑party content that could contain untrusted or user-generated instructions.