audit-design-system
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Figma files through tools like
get_design_contextandget_metadata. While this creates an attack surface for indirect prompt injection, the risk is mitigated by the skill's lack of write access or network capabilities. - Ingestion points: Output from Figma MCP tools (e.g.,
get_design_context,get_variable_defs,get_metadata) as described in the Workflow section of SKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded content are present in the skill instructions.
- Capability inventory: The skill is restricted to read-only Figma tools; there are no file-write, subprocess, or network exfiltration capabilities identified in the instructions or frontmatter.
- Sanitization: No sanitization or validation of the ingested Figma data is performed before processing.
Audit Metadata