ai-clipping
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/polling_results.pyusessubprocess.runto call theopenclawCLI tool for sending progress updates to the agent platform. The call uses a list of arguments without a shell, which prevents command injection. - [EXTERNAL_DOWNLOADS]: The skill makes network requests to the vendor's API endpoints at
wayinvideo-api.wayin.aiandwayin.aifor uploading media, submitting tasks, and polling for results. - [DATA_EXFILTRATION]: The skill uploads local video files to the vendor's cloud infrastructure as part of its core highlight extraction service. This behavior is documented and required for the skill to function as intended.
Audit Metadata