storyboard-design
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill focuses on providing detailed creative and technical instructions for storyboard generation.
- [INDIRECT_PROMPT_INJECTION]: The skill inherently processes external data (advertising briefs and scripts) which constitutes an indirect prompt injection surface. However, it implements robust mitigations through a strict output schema, detailed language constraints (English prompts with quoted Chinese label text), and specific validation rules (e.g., product consistency checks). Ingestion points: advertising briefs and scripts (SKILL.md Workflow); Boundary markers: strict JSON schema and output formatting constraints; Capability inventory: output used by external image/video generators and validators; Sanitization: strict adherence to brief and English-language prompt generation.
- [CREDENTIALS_SAFE]: The skill mentions an environment variable TYPESAFE_API_KEY used for an optional validation step. This is a configuration requirement for external tooling and does not involve hardcoded secrets or credential exfiltration.
Audit Metadata