storyboard-lite
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill primarily performs text analysis and prompt generation based on user-provided script content. It does not utilize dangerous system tools, execute remote code, or access sensitive local files.\n- [EXTERNAL_DOWNLOADS]: The skill references documentation and official model pages for ByteDance's Seedance 2.5 and Higgsfield. These references are provided neutrally for informational purposes and do not involve executable code or untrusted scripts.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied script text to generate storyboards and video prompts. This represents a standard text-processing surface rather than a malicious vector, as the skill lacks any capabilities to perform network exfiltration, file system modifications, or privileged command execution.\n
- Ingestion points: Script text provided by the user in the initial request.\n
- Boundary markers: The skill relies on natural language structure and does not implement technical delimiters for untrusted input.\n
- Capability inventory: Limited to generating Markdown text and tables; no external tool access or system-level capabilities are defined.\n
- Sanitization: Content is processed directly for thematic extraction without secondary filtering.
Audit Metadata