qa-observability

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Fact-Checking" step explicitly instructs the agent to "Use web search/web fetch to verify current external facts" and to validate vendor/docs (i.e., fetch arbitrary public web pages / primary sources), so the agent will ingest untrusted third‑party web content that can materially influence decisions.