amplitude-automation

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTIONNO_CODE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to configure an external MCP server endpoint (https://rube.app/mcp) that is not part of the trusted vendor or service list.\n- [DATA_EXFILTRATION]: The skill routes Amplitude product analytics data, including user identifiers and event properties, through the external Rube MCP infrastructure.\n- [PROMPT_INJECTION]: An indirect prompt injection surface exists as the skill processes external data from Amplitude. Ingestion points: event properties in 'AMPLITUDE_SEND_EVENTS' and user properties in 'AMPLITUDE_IDENTIFY'. Boundary markers: None are defined to separate data from instructions. Capability inventory: Actions are restricted to the provided Amplitude toolkit; no local system shell access or arbitrary code execution is present. Sanitization: No validation or sanitization of input data is mentioned in the skill documentation.\n- [NO_CODE]: This skill contains no local executable code (Python, Node.js, or shell scripts) and is composed entirely of markdown instructions and tool definitions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 09:27 AM