storyboard-to-seedance-prompt
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text files which serves as an attack surface for indirect prompt injection.
- Ingestion points: The skill reads content from a user-specified
文字分镜.txtfile (SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when processing the input file content.
- Capability inventory: The skill has the capability to write multiple
.prompt.txtfiles to the local directory and invoke themultimodal2videotool fromjimeng-skill. - Sanitization: There is no evidence of sanitization, filtering, or validation of the text ingested from the storyboard file before it is processed or written into prompt files.
Audit Metadata