browser-extension-builder

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Prompt Injection (SAFE): No instructions were found that attempt to override AI safety filters or manipulate the agent's core instructions.
  • Data Exposure & Exfiltration (SAFE): The skill uses local browser storage APIs for state management and contains no logic for sending data to external or untrusted domains.
  • Unverifiable Dependencies & Remote Code Execution (SAFE): The project templates do not include external package installations or remote script downloads; all code is self-contained.
  • Dynamic Execution (SAFE): UI injection examples use static HTML templates, avoiding the risk of executing untrusted code via dynamic manipulation.
  • Privilege Escalation (SAFE): The skill explicitly advises against requesting excessive permissions in its anti-patterns section, promoting secure development practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:31 PM