compact-landing
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill workflow includes an instruction for the agent to execute a bundled local Node.js script (
scripts/pick-direction.mjs) to generate design fingerprints. The script uses standard built-in modules (node:crypto) to perform random selection logic and does not engage in network or sensitive file operations. - [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected. The design instructions focus on accessibility, performance (zero layout shift), and creative variety.
Audit Metadata