design-critique

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a prompt-based instruction set focused on providing design feedback and does not contain executable code.
  • [COMMAND_EXECUTION]: The skill reads project configuration files (like package.json) to identify technologies, but these are standard read operations with no execution of file content.
  • [DATA_EXFILTRATION]: No network tools or commands are present; the skill's output is restricted to the local environment and intended for the user.
  • [PROMPT_INJECTION]: The skill instructions do not attempt to bypass agent safety filters or override system constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:59 AM
Security Audit — agent-trust-hub — design-critique