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 addto 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
grepto 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