frontend-design
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- PROMPT_INJECTION (SAFE): The skill uses instructional markers like 'CRITICAL' and 'IMPORTANT' to enforce design standards. These are benign and do not attempt to override the AI's core safety instructions or extract internal prompts.
- DATA_EXFILTRATION (SAFE): There are no commands or instructions that access sensitive files, environment variables, or perform network requests.
- REMOTE_CODE_EXECUTION (SAFE): The skill does not suggest downloading or executing external scripts or unverified packages.
- COMMAND_EXECUTION (SAFE): No shell commands, subprocesses, or system-level operations are defined within the skill.
Audit Metadata