Seedance2-Storyboard-Generator
Analysis
This is an instruction-only storyboard prompt generator with no code, install steps, credentials, or local access, but users should be mindful about media they upload and platform-policy wording.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
Sensitive words: Seedance may reject content with certain terms. Avoid common triggers or use alternative phrasing.
This wording could be interpreted as encouraging users to phrase around platform rejection triggers. It does not show malicious behavior or automatic misuse, but it is a trust and compliance consideration.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
多模态输入(最多12个文件):图片... 视频... 音频... 使用"@素材名"指定用途
The skill’s reference workflow expects user-provided media references to be used with the Seedance platform. This is aligned with video prompt generation, but images, videos, and voice/audio can be sensitive or rights-restricted.
