design-system
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the local project environment to ensure consistency.
- Ingestion points: The skill reads
package.json,tailwind.config.*,src/styles/globals.css, and scanssrc/components/ui/as described inSKILL.md. - Boundary markers: The instructions do not define delimiters or warnings to ignore commands that might be embedded in the files being read.
- Capability inventory: The skill uses file reading commands (
cat,rg) and is intended to generate and write new component files to the source directory. - Sanitization: The skill does not implement validation or sanitization for the project data read by the agent before it influences subsequent generation tasks.
- [COMMAND_EXECUTION]: The skill utilizes local shell commands for environmental discovery.
- Evidence:
SKILL.mddirects the agent to executels,cat,grep, andrgto inspect the project for existing UI components, tokens, and patterns. These commands are limited to local information gathering.
Audit Metadata