ai-storyboard-2x2
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied script content to generate storyboard prompts, creating an attack surface for indirect prompt injection.\n
- Ingestion points: The skill instructions interpolate user-provided scripts and scene descriptions (e.g., "[coller script]", "[description]") directly into the processing flow.\n
- Boundary markers: Absent. There are no explicit delimiters or instructions to treat the user-provided script content as non-executable data.\n
- Capability inventory: The skill generates detailed technical prompts for image models and specifies layouts for design software like Figma.\n
- Sanitization: Absent. The instructions do not specify any validation or filtering of the script input before it is used for prompt generation.
Audit Metadata