Skills
skills/akillness/oh-my-gods/agent-browser/Gen Agent Trust Hub

agent-browser

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Provides instructions to install the browser automation tool from Vercel Labs' official sources.
  • [COMMAND_EXECUTION]: Supports an eval command to execute JavaScript within the browser environment. Documentation recommends using standard input to handle complex scripts securely.
  • [PROMPT_INJECTION]: As the skill interacts with external web data, it identifies the risk of indirect prompt injection and provides mitigation tools, such as the AGENT_BROWSER_CONTENT_BOUNDARIES and AGENT_BROWSER_ACTION_POLICY configurations, to restrict the agent's capabilities when processing untrusted content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 02:48 AM