kelpi

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

• Third-party content exposure detected (high risk: 0.80). The skill connects to the third‑party Kelpi MCP endpoint (https://app.kelpi.ai/api/mcp) and explicitly calls tools like kelpi_workspace_summary, kelpi_get_template, kelpi_open_editor and related APIs to read workspace templates, flows and editor content (user-generated/untrusted content) which the agent is expected to interpret and which can materially influence actions such as creating, updating, or activating flows (see SKILL.md and the references/* files).