figma-use-slides

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted data from user-supplied slide briefs, brand guidelines, and reference files.\n
  • Ingestion points: User-provided instructions for deck content and design language are parsed and used to generate slide structures (SKILL.md, slide-design.md).\n
  • Boundary markers: The skill does not provide specific instructions to the agent for using delimiters or boundary markers to distinguish user-provided content from instructions.\n
  • Capability inventory: The skill utilizes the high-privilege use_figma tool, which has broad access to the Figma Plugin API, including node creation, deletion, and asset uploads (SKILL.md, slide-lifecycle.md).\n
  • Sanitization: There are no explicit instructions for sanitizing or escaping user-provided text before it is interpolated into text nodes within the Plugin API scripts.\n- [DYNAMIC_EXECUTION]: The skill directs the agent to generate and execute JavaScript code snippets at runtime to interact with the Figma environment.\n
  • Execution method: JavaScript code is dynamically constructed by the agent and executed via the use_figma tool to automate slide creation and styling (slide-content.md, slide-gotchas.md).\n
  • Context: While this is the intended primary purpose of the skill, the execution of agent-generated code based on external inputs is a standard technical risk factor.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:10 PM
Security Audit — agent-trust-hub — figma-use-slides