nlweb-llm-providers

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

• Third-party content exposure detected (high risk: 0.75). The required workflow instructs fetching live public GitHub pages (e.g., nlweb-providers.md, config_llm.yaml, config_embedding.yaml) at runtime, and those fetched page bodies are readable text that can be fed into the agent’s LLM context (public web content path: runtime HTTP fetch → parsed text → LLM context).