storyboard-video-orchestrator
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted user data (story ideas, scripts, and visual references) and interpolate it into structured production plans for downstream tools. This creates a standard indirect injection surface inherent to orchestration tasks.
- Ingestion points: User-provided inputs for video goals, target duration, visual styles, and character beats defined in
SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to separate user content from the agent's prompts.
- Capability inventory: The skill itself performs no sensitive operations; it only generates text-based specifications for other tools (video, voice, and audio generators).
- Sanitization: There is no evidence of input validation or escaping for the user-provided data before it is formatted into the final storyboard.
- [SAFE]: The skill references the developer's official repository (tippyentertainment) and the Tasking.tech platform, which are legitimate vendor resources. No unauthorized network activity, credential harvesting, or obfuscation was detected.
Audit Metadata