frontend-design

Fail

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to fetch the complete skill logic from an external, untrusted GitHub repository (Ilm-Alan/frontend-design).
  • [REMOTE_CODE_EXECUTION]: The instructions use npx skills add to download and integrate logic into the agent's environment at runtime. This pattern allows for the execution of unverified remote code from a third-party source.
  • [COMMAND_EXECUTION]: The skill provides specific shell commands for the agent to execute, such as grep to check file contents and [ -e ... ] to probe the existence of directories on the local file system.
  • [PROMPT_INJECTION]: The skill defines a mandatory "Decision tree" that overrides standard agent behavior, forcing the agent to perform installation and environment checks before addressing the user's actual request.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jun 25, 2026, 06:33 PM
Security Audit — agent-trust-hub — frontend-design