product-walkthrough-video
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
node:child_process.spawnAPI to interface withffmpegandffprobe. These tools are used for video encoding, frame-by-frame visual analysis, and media metadata extraction. These processes are executed locally and are essential to the skill's primary function of media processing. - [EXTERNAL_DOWNLOADS]: The skill requires standard developer tools and libraries, specifically
playwright(version 1.63.0) andffmpeg. The documentation provides clear instructions for installing these through official package registries and system package managers like Homebrew and APT. - [DATA_EXFILTRATION]: To prevent accidental data exposure, the skill includes a robust redaction system in
walkthrough-config.mjs. It uses comprehensive regex patterns to detect and mask sensitive information, including GitHub tokens, AWS credentials, and private keys, from browser logs and terminal output. Furthermore, therun-walkthrough.mjsscript facilitates a zero-trust network posture by allowing users to block all external HTTP requests by default.
Audit Metadata