seedance-antislop
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an external GitHub repository (
Emily2040/seedance-2.0) in the YAML metadata and instructions. It specifically mentions loading an external resource,[ref:anti-slop-lexicon], which resolves to a reference corpus located in the associated repository. - [INDIRECT_PROMPT_INJECTION]: The skill functions by ingesting and rewriting user-supplied prompts, creating a surface for indirect prompt injection.
- Ingestion points: The skill is designed to process "Seedance 2.0 prompts" provided by the user.
- Boundary markers: There are no specific delimiters or boundary markers defined in the instructions to isolate the user input from the agent's instructions.
- Capability inventory: The skill contains no scripts, command execution, file writing, or network operations. Its functionality is restricted to text transformation.
- Sanitization: No sanitization or filtering of the input prompt is described in the guidelines.
Audit Metadata