agentation-self-driving

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses agent-browser to open and snapshot a user-specified web page at runtime, ingesting the page’s DOM/text (outsider-authored public web content) into the agent’s LLM context via agent-browser snapshot -i output and subsequent eval-driven reads.