antfly-cli

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

• Third-party content exposure detected (high risk: 0.80). The skill's RAG interactive example (Workflow 5: "Interactive chat mode") explicitly passes --tools "websearch,fetch", which indicates the agent will fetch and read arbitrary public web content (untrusted third‑party pages) as part of its retrieval/decision pipeline, so external pages could indirectly inject instructions.