ai-orchestration-langchain

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

• Third-party content exposure detected (high risk: 0.90). The skill's RAG and agent examples (examples/rag.md and indexing.ts) explicitly load arbitrary web pages using CheerioWebBaseLoader (e.g., new CheerioWebBaseLoader("https://example.com/...")) and pass the retrieved public document content into retrievers/agents as context or via a retrieve_documents tool, meaning untrusted third-party content is read and can materially influence agent decisions (allowing indirect prompt injection).