design-system-audit
Warn
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use
npx saglitzdesign-mcp, which downloads a package from the public npm registry at runtime. - [REMOTE_CODE_EXECUTION]: The use of
npxresults in the execution of remote code within the agent's environment. The source of this package (saglitzdesign-mcp) is not associated with a known trusted vendor. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external codebase content, such as stylesheets and component files, which provides an attack surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: Reads stylesheets, theme files, and component source code from the user's project to perform the audit.
- Boundary markers: No specific delimiters or "ignore" instructions are prescribed for the ingested code content.
- Capability inventory: The skill uses tools to audit code, generate new style systems, and perform linting, which involves both reading and writing to the file system.
- Sanitization: There is no evidence of sanitization or validation of the ingested code content before it is processed by the AI.
Audit Metadata