byted-seedance-video-generate
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input that is interpolated into network requests to an external API service, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: Prompt text and multiple media URLs (images, videos, and audio) provided via function parameters and command-line arguments in
scripts/video_generate.py. - Boundary markers: The skill does not employ delimiters or instructions to the model to ignore potential instructions embedded within the user-provided content.
- Capability inventory: The skill performs authenticated HTTP POST and GET requests to
ark.cn-beijing.volces.comusing thehttpxlibrary. - Sanitization: No input validation or sanitization is performed on the user-supplied strings and URLs before they are included in the JSON request body sent to the remote API.
Audit Metadata