design
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: Local scripts are executed to perform design analysis. This execution is limited to local file paths, and the 'design-tools.mjs' entry point includes explicit validation to prevent network-based attacks like SSRF by rejecting URL-style inputs.
- [EXTERNAL_DOWNLOADS]: The skill utilizes the standard 'Pillow' Python library for image decoding and processing. It does not initiate any unauthorized downloads of external code or binaries at runtime.
- [SAFE]: No malicious patterns, prompt injections, obfuscation, or persistence mechanisms were detected in the skill instructions or associated scripts.
Audit Metadata