videoagent-video-studio
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill communicates with an external proxy at
https://video-gen-proxy.vercel.appto facilitate video generation without requiring local API keys. This is documented as a primary feature. - [COMMAND_EXECUTION]: The skill requires the agent to execute a local Node.js script,
tools/generate.js, to process generation requests and communicate with the proxy. - [PROMPT_INJECTION]: The skill handles untrusted user input (prompts and image URLs) that is forwarded to external video generation APIs. Evidence: 1. Ingestion points:
tools/generate.js(via --prompt and --image-url). 2. Boundary markers: None used for user-provided strings. 3. Capability inventory: Network access via the fetch API intools/generate.js. 4. Sanitization: Input strings are used directly without sanitization.
Audit Metadata