mixpanel-automation

Warn

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external third-party MCP server.\n
  • Evidence: The setup instructions direct users to add https://rube.app/mcp as an MCP server endpoint.\n- [REMOTE_CODE_EXECUTION]: The skill facilitates the execution of dynamic scripts and remote tools.\n
  • Evidence: The MIXPANEL_JQL_QUERY tool allows the execution of custom JavaScript code. The use of a remote MCP server inherently involves the execution of externally defined tools.\n- [DATA_EXFILTRATION]: Sensitive analytics and user profile data are processed through an external infrastructure.\n
  • Evidence: Data retrieved via tools like MIXPANEL_QUERY_PROFILES and MIXPANEL_AGGREGATE_EVENT_COUNTS is processed by the external service located at rube.app.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to the ingestion and processing of untrusted external data.\n
  • Ingestion points: Analytics event data and user profiles processed by tools defined in SKILL.md.\n
  • Boundary markers: None identified; the skill lacks explicit instructions to ignore embedded commands in the data.\n
  • Capability inventory: The skill possesses write capabilities (MIXPANEL_PROFILE_BATCH_UPDATE) and script execution capabilities (MIXPANEL_JQL_QUERY) as described in SKILL.md.\n
  • Sanitization: No evidence of data sanitization or validation was found in the skill's instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 11, 2026, 11:52 PM
Security Audit — agent-trust-hub — mixpanel-automation