design-system
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing an additional skill from the author's repository using
npx skills add jwilger/agent-skills. This is a reference to a vendor-owned resource. - [COMMAND_EXECUTION]: Recommends the execution of a shell command (
npx) to add skill dependencies to the environment. - [PROMPT_INJECTION]: Identified an Indirect Prompt Injection surface (Category 8) as the skill is designed to ingest and process user-supplied design principles and preferences. * Ingestion points: User dialogue and responses during the 7-phase process described in references/design-phases.md. * Boundary markers: The skill does not explicitly define delimiters to isolate user-provided text within the generated documentation. * Capability inventory: The skill possesses the capability to write files (docs/design-system.html or docs/design-system.pen) based on gathered input. * Sanitization: There is no documented mechanism for sanitizing or escaping user-provided strings before they are included in the final artifact.
Audit Metadata