figma-generative-plugins
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a legitimate development workflow for Figma plugins, adhering to the platform's architectural requirements (sandbox vs UI) and utilizing official Figma domains for tool testing. It includes proactive security instructions such as the prohibition of embedding API keys or OAuth tokens and the requirement to bound computational work.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it requires the agent to read existing plugin source code to use as a source of truth for updates. This behavior is necessary for the skill's primary purpose of code maintenance.
- Ingestion points: Source code URIs retrieved via
get_generative_plugin(SKILL.md). - Boundary markers: Absent; the agent is instructed to treat the entire file content as the source of truth.
- Capability inventory: The skill uses
create_generative_pluginandupdate_generative_pluginto deploy logic to the Figma environment. - Sanitization: Absent; there is no explicit instruction to sanitize or filter the content of retrieved files before processing.
Audit Metadata