web-asset-generation
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses the legitimate 'sharp' library for image manipulation and 'fs' for file operations, consistent with its documented purpose.
- [COMMAND_EXECUTION]: The code utilizes 'mkdirSync' and 'sharp.toFile()' to write generated assets to the local disk.
- [DATA_EXFILTRATION]: No outbound network calls or exfiltration patterns were detected in the analysis.
- [PROMPT_INJECTION]: The instructions and implementation do not contain any patterns aimed at subverting agent behavior or safety controls.
Audit Metadata