icon-set-generator

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns were detected. The skill operates within a controlled environment, reading local configuration and reference files to generate icon assets.
  • [COMMAND_EXECUTION]: The skill generates SVG and HTML files in a local icons/ directory. This is the primary intended function of the skill and does not involve executing arbitrary system commands.
  • [DATA_EXFILTRATION]: No network activity or sensitive data access was identified. The skill generates content locally based on user input and provided templates.
  • [PROMPT_INJECTION]: The instructions provide clear operational guidelines for the agent and do not contain patterns typical of behavior overrides or safety filter bypasses.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided project descriptions to suggest and generate icons. While this constitutes an untrusted data ingestion surface, the risk is mitigated by strict SVG templates and a quality checklist that limits output to specific graphic elements (paths, circles, etc.), preventing the generation of executable payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 01:36 PM