basecamp-automation

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to configure a remote MCP server at https://rube.app/mcp. This is a documented endpoint for the Rube/Composio toolkit that provides the Basecamp integration functionality.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it reads data from Basecamp message boards and to-do lists that could potentially contain instructions. \n
  • Ingestion points: Data is brought into the agent context via retrieval tools such as BASECAMP_GET_MESSAGE and BASECAMP_GET_BUCKETS_TODOLISTS_TODOS. \n
  • Boundary markers: The instructions do not define explicit delimiters to isolate external data from system instructions. \n
  • Capability inventory: The tool includes write capabilities such as BASECAMP_CREATE_MESSAGE, BASECAMP_POST_BUCKETS_TODOLISTS_TODOS, and project access management through BASECAMP_PUT_PROJECTS_PEOPLE_USERS. \n
  • Sanitization: The skill notes that Basecamp requires HTML formatting and that the API validates tags, providing a basic structural sanitization layer.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:24 PM
Security Audit — agent-trust-hub — basecamp-automation