raspberrypi

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

• Third-party content exposure detected (low risk: 0.10). The agent reads user-generated project content and pages from raspberrypi.org via search and read tools, representing low-risk ingestion of third-party public web content.

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 third-party MCP server (https://unbrowse.ai/mcp/raspberrypi.org) and fetch instructions/tools from it at runtime, which constitutes an unofficial external operational dependency with common/reputable third-party provenance.