mixpanel-automation

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it retrieves and processes data from Mixpanel APIs which could contain attacker-controlled content.\n
  • Ingestion points: Data is ingested from Mixpanel via tools such as MIXPANEL_QUERY_PROFILES, MIXPANEL_AGGREGATE_EVENT_COUNTS, and MIXPANEL_COHORTS_LIST (SKILL.md).\n
  • Boundary markers: No explicit delimiters or instructions are provided to help the agent distinguish between data and instructions.\n
  • Capability inventory: The skill has write capabilities through MIXPANEL_PROFILE_BATCH_UPDATE and can execute scripts via MIXPANEL_JQL_QUERY (SKILL.md).\n
  • Sanitization: There is no evidence of sanitization or validation of the external data before it is processed.\n- [DYNAMIC_EXECUTION]: The skill facilitates the execution of JQL (JavaScript Query Language) scripts through the MIXPANEL_JQL_QUERY tool. This is an intended feature of the Mixpanel API for advanced querying.\n- [EXTERNAL_DOWNLOADS]: The setup instructions require the user to configure an external MCP server endpoint (https://rube.app/mcp) to enable the Mixpanel toolkit functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 04:32 PM
Security Audit — agent-trust-hub — mixpanel-automation