amplitude-automation

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

• Third-party content exposure detected (high risk: 0.90). This skill's required workflow explicitly directs the agent to call RUBE_SEARCH_TOOLS (e.g., https://rube.app/mcp) to fetch tool schemas and to call Amplitude APIs like AMPLITUDE_GET_EVENT_CATEGORIES and AMPLITUDE_LIST_COHORTS / AMPLITUDE_GET_USER_ACTIVITY to read user-configured event names, cohorts, and activity — untrusted third‑party content that the agent must interpret and that can change tool usage and subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill requires connecting to Rube MCP at runtime ("Add https://rube.app/mcp" and "RUBE_SEARCH_TOOLS" to fetch current tool schemas), so the external endpoint is a required runtime dependency that can change the agent's available tools/instructions and thus directly control agent behavior.