seedance-2-5
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external multimodal data through various URL-based parameters, creating a surface for indirect prompt injection where malicious instructions could be embedded in the assets or their metadata.
- Ingestion points: The skill utilizes
image_urls,video_urls,audio_urls,references,referenceVideos, andreferenceAudioacross different provider routes described inSKILL.md. - Boundary markers: There are no explicit instructions or delimiters provided to isolate the model from potentially malicious instructions contained within these external assets.
- Capability inventory: The skill enables the execution of video generation tool calls (
seedance_video,seedance_ark,runway_video,comfyui_video) which process this external data. - Sanitization: The skill does not mention any validation, filtering, or sanitization processes for the content retrieved from external URLs.
Audit Metadata