cx-agent-studio

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly enables and instructs the agent to fetch and consume public third‑party content (e.g., Google Search, website data stores, and arbitrary HTTP requests via ces_requests) as shown in SKILL.md Quick Actions ("Add Tools") and detailed in references/tools.md, and those external results are used by tools/callbacks to shape responses and control flows—exposing the agent to untrusted web/user-generated content that can influence actions.