orca-cli

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

• Third-party content exposure detected (high risk: 0.75). Runtime LLM context can be fed by outsider-authored free text when the skill uses the built-in browser to orca goto/snapshot/pdf/console/network and then the agent consumes the page content or console/network text, which originates from arbitrary external web pages (public web content fetched at runtime).