pencil-ui-designer

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines instructional logic for an orchestration agent and does not include any executable code, file system access, or network capabilities.
  • [PROMPT_INJECTION]: The skill uses emphasized instructions (labeled as CRITICAL) to restrict its own activation to specific user triggers, which serves as a relevance and safety filter rather than a bypass mechanism.
  • [EXTERNAL_DOWNLOADS]: No external packages or remote scripts are referenced or downloaded.
  • [DATA_EXFILTRATION]: There is no evidence of hardcoded credentials or mechanisms to access and exfiltrate sensitive information.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 05:22 PM