answers

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

• Third-party content exposure detected (high risk: 0.90). The skill calls the Brave Search API (https://api.search.brave.com/res/v1) and in research mode (enable_research=true) performs iterative web searches, analyzes and synthesizes content from discovered URLs (see , , and citation tags), so it ingests untrusted public web content that the agent reads and uses in its answers.