skills/mixpanel/ai-plugins/install/Gen Agent Trust Hub

install

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands to check for existing installations (mp --version), install the Python SDK (pip install mixpanel-headless), and configure the MCP server (claude mcp add). These are standard administrative tasks necessary for the skill's purpose.
  • [REMOTE_CODE_EXECUTION]: Fetches and installs the mixpanel-headless Python package and uses npx to execute the mcp-remote utility. These resources originate from official registries and target Mixpanel's infrastructure, which is consistent with the skill's verified author.
  • [PERSISTENCE_MECHANISMS]: Optionally records engine preferences by appending instructions to project configuration files like CLAUDE.md or AGENTS.md. This behavior is intended for session persistence and explicitly requires user confirmation before any modifications are made.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read agent-specific instructions from a CLAUDE.md file bundled within the installed mixpanel-headless package directory.
  • Ingestion points: The path mixpanel_headless/CLAUDE.md is accessed via a Python one-liner in references/headless-setup.md.
  • Boundary markers: None; the content is read directly as instructions.
  • Capability inventory: The skill has permissions to install packages, configure MCP servers, and run project-specific CLI tools.
  • Sanitization: No sanitization is performed on the file content before it is read into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 01:46 PM