mixpanel-data

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the mp CLI and Python scripts for data pipeline management.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and configuration files from jaredmcfarland.github.io. This is a standard practice for fetching software documentation and does not include execution of untrusted scripts.
  • [PROMPT_INJECTION]: The skill exposes a surface for Indirect Prompt Injection (Category 8) by ingesting untrusted data from an external API (Mixpanel).
  • Ingestion points: Untrusted data enters the agent context through fetch_events, fetch_profiles, and live segmentation queries.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to encapsulate fetched JSON property values.
  • Capability inventory: The skill enables shell execution, local DuckDB SQL queries, and Python script generation.
  • Sanitization: There is no evidence of property sanitization or escaping before the data is processed or output to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 08:57 PM