create-design-system-rules
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it processes external design data from a Figma MCP server to generate architectural and styling rules that are persisted in the project's configuration.
- Ingestion points: Data retrieved from Figma nodes via MCP tool calls like get_design_context and get_metadata.
- Boundary markers: Absent; there are no specified delimiters or instructions to ignore embedded commands within the fetched design data.
- Capability inventory: The skill analyzes the local codebase structure and has the capability to write generated rules to the CLAUDE.md file in the project root.
- Sanitization: The skill does not perform validation or escaping of the external content before incorporating it into the behavioral rule set.
Audit Metadata