base-ui-primitive-composition
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to ingest and act upon data from external Figma design files.
- Ingestion points: The skill reads from Figma selection, frames, components, instances, variables, styles, layers, prototype settings, comments, sections, and annotations as defined in the 'Supported Context' section of
SKILL.md. - Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore potentially malicious instructions embedded within Figma comments or annotations.
- Capability inventory: The skill is limited to generating code snippets, implementation plans, and mapping documentation. It does not have access to execute shell commands, write files, or perform network operations.
- Sanitization: The instructions do not specify any sanitization, filtering, or validation of the content ingested from Figma context before it is processed by the model.
Audit Metadata