llm-context

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

• Third-party content exposure detected (high risk: 1.00). Brave's LLM Context API (/res/v1/llm/context) explicitly fetches and returns extracted content from arbitrary public web pages (grounding.generic[].url and snippets), which the agent ingests to ground responses and therefore exposes it to untrusted/user-generated third‑party content.