motion-graphic-gen
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFEPROMPT_INJECTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill's workflow involves taking user-provided content and design language and passing it verbatim into a brief for a downstream code-generation model. This creates a surface for indirect prompt injection where malicious instructions could be embedded in user content.
- Ingestion points: User content and design words collected in SKILL.md.
- Boundary markers: No delimiters or ignore instructions are specified for the prompt composition.
- Capability inventory: The submit_motion_graphic tool triggers generation and execution of JSX code in the platform renderer.
- Sanitization: No explicit validation or filtering of user input strings is mentioned.
- [REMOTE_CODE_EXECUTION]: The skill is designed to generate and modify executable JSX code for animations. This dynamic execution risk is mitigated by the hard constraints in references/design-principles.md, which prohibit import statements, TypeScript, and the use of external URLs in the code. This ensures the generated code can only access pre-injected safe globals.
- [EXTERNAL_DOWNLOADS]: The skill outlines a standard process for downloading external media assets into the project sandbox so they can be registered and used in animations. This is a documented, legitimate administrative capability for managing media pool assets.
Audit Metadata