seedance-shotlist-interview
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for an agent to act as a creative director during an interview process. It does not perform any dangerous operations, execute code, or access the file system.
- [PROMPT_INJECTION]: The skill processes untrusted user input (vague ideas and concepts) to generate film treatments. While it does not explicitly define boundary markers for this data, it lacks dangerous capabilities (such as shell execution, network access, or file writing) that could be exploited by an indirect prompt injection.
- [DATA_EXFILTRATION]: No sensitive data access or network transmission patterns were detected. The repository link in the metadata points to the author's own GitHub profile, which is standard for public skill documentation.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute external scripts, nor does it include any package dependencies.
Audit Metadata