Skills
Navigate
skills/nyldn/agentation/agentation-self-driving/Gen Agent Trust Hub

agentation-self-driving

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill employs bash to execute agent-browser commands for launching the browser, managing sessions, and taking snapshots of the target web page.
  • [REMOTE_CODE_EXECUTION]: The skill uses agent-browser eval to run JavaScript snippets directly in the browser's execution context. This is used for standard automation tasks such as element scrolling, bounding box calculation, and interaction with the DOM to detect and manipulate the Agentation toolbar components.
  • [EXTERNAL_DOWNLOADS]: The instructions describe a workflow where annotations are transmitted to an external MCP server. This is a documented feature of the Agentation tool and represents intended functionality for a design critique workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 05:43 AM
Security Audit — agent-trust-hub — agentation-self-driving