seedance-lighting
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions for prompt generation. No malicious code, obfuscation, or unauthorized access patterns were identified.- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting user-supplied "mood words" and project briefs.
- Ingestion points: User input and external reference files (e.g.,
directors-read.md). - Boundary markers: None specified to delimit user content from instructions.
- Capability inventory: The skill performs text generation only; no file system access, network requests, or subprocess execution capabilities are present.
- Sanitization: Not present, as the data is used for classification and descriptive output rather than execution.
Audit Metadata