motion-canvas-agent
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by extracting and processing text labels from the Motion Canvas scene graph.
- Ingestion points: The
GET /__agent/scene-graphendpoint inassets/agent-plugin.tsretrieves data from the browser context using theserializeNodefunction inassets/agent-client.ts. - Boundary markers: The output format does not utilize boundary markers to distinguish extracted scene text from agent instructions.
- Capability inventory: The skill provides capabilities for seeking frames, controlling playback, modifying project settings (size, background), and triggering file rendering.
- Sanitization: The
assets/agent-client.tsfile includes basic sanitization that strips control characters and truncates extracted text to 100 characters to mitigate malformed input risks.
Audit Metadata