storyboard-builder
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an architectural surface for indirect prompt injection because it processes content from external files (
concept.mdandshot-list.md) to populate templates for downstream AI models. This is an expected design pattern for this skill's functionality. - Ingestion points: Reads from
shot-list.mdandconcept.mdin Step 1. - Boundary markers: No explicit delimiters or boundary markers are defined in the output templates to isolate ingested content.
- Capability inventory: The skill is limited to generating text prompts and does not possess capabilities for code execution, system modification, or network exfiltration.
- Sanitization: Content is interpolated directly into templates without validation or sanitization.
- [EXTERNAL_DOWNLOADS]: The skill references well-known technology services and AI models such as Seedance 2.0 and GPT Image 2. These are standard tool references within the expected use-case and do not represent a security risk.
Audit Metadata