seedance-video-prompt
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No signs of obfuscation, malicious code execution, or unauthorized data exfiltration were found. The skill instructions are clearly defined and follow a logical workflow for their stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it ingests user-provided text and images to construct prompts. However, this risk is mitigated by the requirement for the agent to follow strict templates and formulas defined in the local reference files, which constrains the output format and prevents the agent from following external instructions. This is considered a low-risk characteristic inherent to the skill's primary function.
Audit Metadata