video-toolkit
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill manages its environment by installing necessary Python and Node.js dependencies from standard package registries using
pip3andnpm. - [REMOTE_CODE_EXECUTION]: It uses the
modalCLI to deploy and execute AI inference scripts on Modal's cloud GPU infrastructure, which is the intended method for processing heavy AI tasks like voiceover, image generation, and video synthesis. - [DATA_EXFILTRATION]: The toolkit uses a local
.envfile to store and manage configuration details and API credentials (such as HuggingFace tokens and Cloudflare R2 credentials), which is a common and accepted practice for local development tools to avoid hardcoding secrets. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text briefs and scripts as inputs for various remote AI models. This is a standard functional surface for a content generation tool and does not represent a bypass of agent security controls.
Audit Metadata