basecamp-automation

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads Basecamp projects, to-dos, messages, and comments which can contain outsider-authored text injected by project members or external collaborators.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill references https://rube.app/mcp as an endpoint configuration instruction for the Rube MCP server, which constitutes an operational dependency with unknown/third-party provenance, resulting in a high risk rating.