mixpanel-automation

Warn

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires connecting to an external MCP server at https://rube.app/mcp to function. This third-party service mediates all interactions between the agent and Mixpanel.
  • [REMOTE_CODE_EXECUTION]: Includes the MIXPANEL_JQL_QUERY tool, which allows the agent to execute arbitrary JavaScript Query Language (JQL) scripts. This provides a mechanism for remote logic execution on the Mixpanel backend.
  • [DATA_EXFILTRATION]: The architecture routes sensitive product analytics, including user profiles and event data, through the rube.app infrastructure.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes data from Mixpanel that may be controlled by external users (e.g., user profile properties or event attributes). Ingestion points: MIXPANEL_QUERY_PROFILES and MIXPANEL_AGGREGATE_EVENT_COUNTS in SKILL.md. Boundary markers: None identified in the instructions to separate data from instructions. Capability inventory: MIXPANEL_PROFILE_BATCH_UPDATE (writing data), MIXPANEL_JQL_QUERY (script execution), and MIXPANEL_QUERY_SEGMENTATION in SKILL.md. Sanitization: No explicit sanitization or validation of the ingested data is described.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 19, 2026, 07:04 PM