agentation

Warn

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill initiates the installation of the agentation package and the execution of agentation-mcp via npx. These packages are retrieved from public registries and are not from the defined list of Trusted External Sources.
  • [COMMAND_EXECUTION] (MEDIUM): The skill executes multiple shell commands including npm install, claude mcp list, and claude mcp add. These commands modify the local project environment and the agent's configuration.
  • [Persistence Mechanisms] (MEDIUM): By running claude mcp add agentation -- npx agentation-mcp server, the skill establishes a persistence mechanism where the agentation-mcp code is executed every time the Claude Code environment is initialized. While this is part of the intended setup, it represents a high-privilege persistent operation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 18, 2026, 11:03 AM