figma-use-slides
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data including user-provided design briefs, brand guidelines, and existing Figma file content to generate or modify slide decks.
- Ingestion points: The agent reads user prompts, Figma file metadata, and slide content through the
use_figmatool as described inSKILL.mdandreferences/slide-gotchas.md. - Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the processed Figma data.
- Capability inventory: The skill leverages tools for canvas manipulation, file creation, and image uploads (
use_figma,upload_assets). - Sanitization: The skill relies on the underlying Figma Plugin API sandbox and the agent's internal safety guardrails rather than implementing custom sanitization logic.
- [EXTERNAL_DOWNLOADS]: The
CHANGELOG.mdneutrally references a vendor repository atgithub.com/figma/mcp-server-guidefor synchronization purposes. This is an official source for the tool's documentation and does not involve automated remote code execution.
Audit Metadata