agentcore

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

• Third-party content exposure detected (high risk: 0.85). The required workflow is to run chrome-use against a user-supplied URL (e.g., chrome-use -p agentcore open https://example.com), which can cause the agent to ingest arbitrary public web page text at runtime (public web content category via browser page load/scrape into LLM context).