googlephotos-automation

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

• Third-party content exposure detected (high risk: 0.80). The skill accepts arbitrary web URLs for uploads (the url parameter in GOOGLEPHOTOS_UPLOAD_MEDIA and urls/media_files in GOOGLEPHOTOS_BATCH_CREATE_MEDIA_ITEMS), so the agent will fetch and ingest untrusted third-party content from the open web as part of its workflow, enabling indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires adding and using the MCP server at https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS) to fetch current tool schemas that directly control the agent's prompts/tool behavior and are a required dependency.