video-prompt
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely focused on prompt engineering for video generation. It defines strict formatting rules for time-segmented prompts (e.g., '0-3秒：...').
- [COMMAND_EXECUTION]: The skill mentions the use of
update_storyboardto save generated prompts. This is a functional requirement of the skill's purpose and does not involve arbitrary command execution or shell access. - [PROMPT_INJECTION]: No patterns associated with prompt injection, safety bypass, or behavioral overrides were found. The instructions are descriptive and narrow in scope.
- [DATA_EXFILTRATION]: There are no network calls, external URLs, or attempts to access sensitive system files like credentials or environment variables.
- [REMOTE_CODE_EXECUTION]: The skill does not perform any package installations (pip/npm) or download external scripts for execution.
Audit Metadata