dify-dsl-generator

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

• Third-party content exposure detected (high risk: 0.80). The skill's generated workflows include HTTP Request nodes (e.g., the "HTTP Request 节点" with a url field) and tool/builtin nodes that call external APIs/search, and the agent/LLM is expected to read and process those external API/URL responses as part of the workflow, exposing it to untrusted third‑party content.