website-screenshot-notte

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

• Third-party content exposure detected (high risk: 0.70). The workflow uses runtime curl calls to a proxy endpoint to navigate to a user-supplied website URL (/sessions/{session_id}/page/execute with body.url), which causes the browser to fetch outsider web page content that can be ingested into the agent’s LLM context via the screenshot/navigation toolchain (indirect prompt injection risk).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill issues runtime curl requests to the Gooseworks proxy endpoint (e.g. https://api.gooseworks.ai/v1/proxy/orthogonal/run) which causes the remote service to start and control browser sessions (i.e., execute remote code) and is required for the skill to function.