figma
Pass
Audited by Gen Agent Trust Hub on Nov 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a local command-line interface, defined as
npx hyperframes, which is mapped to a local script (plugin-cli.mjs) within the skill's directory. It also usesffmpegandffprobevia theverify-motion.mjsscript to compare render output against reference videos for fidelity. - [DYNAMIC_EXECUTION]: The skill dynamically generates JavaScript-based animation timelines using the GreenSock Animation Platform (GSAP). These scripts are generated from Figma motion data and injected into video compositions.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Figma, creating a potential surface for indirect injection if malicious data is present in design files.
- Ingestion points: Responses from the Figma REST API, motion.dev code snippets, and Figma file URLs provided by the user (found in
SKILL.md). - Boundary markers: Absent; the skill does not explicitly use delimiters to separate external data from instructional content during processing.
- Capability inventory: The skill can read environment variables (FIGMA_TOKEN), write to the local file system (assets and caches), and execute shell commands or generated JavaScript.
- Sanitization: The skill employs a normalization function (
motionContextToDocs) to map raw external data into a strict internal schema before generating code, which acts as a structural validation layer.
Audit Metadata