design-debt-audit

Fail

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill functions as a pointer (stub) that directs the agent to fetch its full implementation from an unverified external source at https://github.com/Owl-Listener/designer-skills. Installing and executing code from unknown third-party repositories bypasses security boundaries established for the local skill environment.
  • [COMMAND_EXECUTION]: The skill provides specific shell commands for the agent to execute, including status checks via grep and package installation via npx skills add. These commands are designed to modify the agent's persistent environment by adding new executable capabilities from the internet.
  • [COMMAND_EXECUTION]: The documentation explicitly instructs the agent to use the ! prefix—a feature in certain environments like Claude Code that triggers direct shell execution—to run the installation commands. This encourages the agent to bypass conversational safety guardrails and perform autonomous system modifications.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jun 16, 2026, 01:27 PM
Security Audit — agent-trust-hub — design-debt-audit