create-onboarding-video
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data (screenshots and feature descriptions) to generate Remotion code, creating a potential surface for indirect prompt injection.
- Ingestion points: The 'Intake' workflow in
SKILL.mdcollects screenshots and intent text from the user. - Boundary markers: Absent; there are no specific instructions for the agent to ignore or sanitize instructions that might be embedded within the user-provided images or descriptions.
- Capability inventory: The skill generates and writes TypeScript/React code (
.tsx) and manages static assets in thepublic/directory. - Sanitization: Absent; the agent is directed to match the app's design language and language directly from the provided stills.
- [DYNAMIC_EXECUTION]: The skill is designed to generate executable code for the Remotion framework.
- The agent generates
.tsxscene files and component files (src/scenes/,src/components/Cursor.tsx) based on templates provided inresources/cursor-component.mdand logic inSKILL.md. - This dynamic code generation is the primary, intended purpose of the skill for video production and uses standard UI development patterns.
Audit Metadata