rozenite-agent

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

• Third-party content exposure detected (high risk: 0.90). The skill's network and network-activity domains (domains/network.md and domains/network-activity.md) instruct the agent to record HTTP/HTTPS traffic and fetch request/response bodies via getRequestBody/getResponseBody, meaning the agent will ingest arbitrary external web content from third-party servers that could contain malicious instructions.