orf-at

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

• Third-party content exposure detected (low risk: 0.10). The agent reads news articles, weather forecasts, and web pages from orf.at via Unbrowse MCP tools, exposing it to public news site content (low risk for arbitrary web/content fetching).

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to connect to an external Model Context Protocol server hosted at an unofficial third-party domain (unbrowse.ai), which acts as an operational runtime dependency providing tools and instructions.