motion-design
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied assets, references, and scripts to generate executable HTML/JS code using the GSAP library. This creates a surface for indirect prompt injection if the input content is not properly isolated.
- Ingestion points: Processes user briefs, references, and scripts as described in the "Resolve the brief without stalling" section of SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or specific warnings to isolate untrusted user data from the generation instructions.
- Capability inventory: The skill generates executable HTML/JS files and utilizes platform CLI tools (media scaffold, media generate) to write to the filesystem and perform video rendering (SKILL.md).
- Sanitization: No explicit sanitization, escaping, or validation mechanisms for user-provided input are described before its interpolation into the generated animation code.
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute specific platform-provided CLI tools ($OD_BIN) using environment variables ($OD_NODE_BIN, $OD_PROJECT_ID) for scaffolding projects and rendering video content. These operations are conducted using native shell tools provided by the host environment.
Audit Metadata