storyboard-grid-to-video
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references several external URLs for 'Case evidence' (e.g.,
goodcase.ai,media.goodcase.ai,x.com). These are used to provide the AI with examples of finished media and prompt strategies to ensure visual fidelity. No executable code is downloaded or run from these sources. - [REMOTE_CODE_EXECUTION]: There are no patterns involving shell execution, dynamic script loading, or package installations. The workflow is entirely prompt-based.
- [DATA_EXFILTRATION]: The skill explicitly includes a safety rule: 'Do not publish, purchase, upload private assets, or make external account changes without explicit user approval.' No commands exist that would read or send sensitive system data.
- [PROMPT_INJECTION]: The instructions contain strict constraints and safety guidelines ('Do not invent...', 'Do not imply...'). The instructional language ('IMPORTANT', 'Required evidence gate') is used for workflow compliance rather than bypassing safety filters.
- [DYNAMIC_CONTEXT_INJECTION]: No
!command`` syntax or load-time shell executions were detected.
Audit Metadata