openai-assistants

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

• Third-party content exposure detected (high risk: 0.80). The skill ingests and processes untrusted user/third‑party documents (via openai.files.create, vectorStores.files.create and the file_search/vector store features, and attachments processed by the code_interpreter) which the assistant is expected to read and use for answers, creating a clear avenue for indirect prompt injection.