seedance-storyboard-generator
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed purely of natural language instructions and templates for creative writing and prompt engineering. It does not include any executable scripts, binary files, or system-level commands. It does not attempt to access sensitive files or perform network operations beyond the scope of a standard LLM conversation.
- [SAFE]: No indicators of data exfiltration or credential theft were detected. References to external platforms like Suno, Udio, and ElevenLabs are provided as user recommendations for audio production and do not represent internal network calls or secret harvesting.
- [SAFE]: No obfuscation, persistence mechanisms, or privilege escalation attempts were identified within the provided markdown instructions or reference guides.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user content, such as novels, articles, or story outlines, to generate scripts. This constitutes a standard ingestion point for indirect prompt injection. However, the risk is evaluated as low because the agent is instructed to follow a strict structural analysis and script format, which inherently limits the execution of embedded instructions. No specific boundary markers for user input are defined in the instructions.
Audit Metadata