varg-previz
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill implements a legitimate local development environment for video planning. It contains a local HTTP server (
serve.py) to host a three.js application, which is a standard pattern for interactive AI agent tools. - [COMMAND_EXECUTION]: The skill utilizes
subprocess.runinbuild_pack.pyto executeffmpegfor video encoding and concatenation. These calls use argument lists rather than raw shell strings, which is a safe practice that prevents command injection. The usage of FFmpeg is central to the skill's purpose of building video reference packs. - [DATA_EXPOSURE]: The local server in
serve.pyimplements a_local()security check. This check validates that theHostheader islocalhostor127.0.0.1and ensures that anyOriginheader matches the local server, preventing Cross-Site Request Forgery (CSRF) or unauthorized remote access to the local save/export APIs. - [FILE_SYSTEM]: The
/api/exportand/api/saveendpoints in the local server are restricted. The export function specifically enforces that only files ending in.mdcan be written to the project directory, and it uses the.nameattribute to prevent path traversal attacks. - [EXTERNAL_DOWNLOADS]: The skill references standard three.js libraries and utilizes Playwright for headless browser frame capture. All external service references (e.g.,
varg.ai,s3.varg.ai) are consistent with the vendor's own infrastructure and the primary purpose of the skill.
Audit Metadata