mixpanel-automation

Warn

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill relies on an external MCP endpoint at https://rube.app/mcp to provide tool schemas and execution logic. This introduces a dependency on third-party infrastructure for core functionality.
  • [COMMAND_EXECUTION]: The tool MIXPANEL_JQL_QUERY facilitates dynamic execution of user-provided JavaScript scripts (JQL) within the Mixpanel platform context. While a standard feature of the analytics platform, it represents a dynamic code execution surface.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8) due to its data processing workflows.
  • Ingestion points: Reads external data including user profiles, cohorts, and event properties via MIXPANEL_QUERY_PROFILES, MIXPANEL_COHORTS_LIST, and MIXPANEL_AGGREGATE_EVENT_COUNTS.
  • Boundary markers: None identified. The instructions do not specify the use of delimiters or 'ignore' instructions when processing data from Mixpanel.
  • Capability inventory: Includes write capabilities through MIXPANEL_PROFILE_BATCH_UPDATE and script execution via MIXPANEL_JQL_QUERY.
  • Sanitization: There is no documented mechanism for sanitizing or validating data retrieved from the analytics platform before it is interpreted by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 09:36 AM