interface-design-system
Warn
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The manual installation method directs users to clone a repository from an untrusted source (https://github.com/Dammyjay93/interface-design.git).
- [REMOTE_CODE_EXECUTION]: The installation process requires moving unverified external code into agent configuration directories (~/.claude/ and ~/.claude-plugin/), facilitating the execution of code from an unknown source.
- [COMMAND_EXECUTION]: Setup involves executing shell commands, including git clone and recursive copy operations, to install the skill.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from project files, creating a vulnerability surface.
- Ingestion points: Reads design system configuration from .interface-design/system.md and audits project source code in src/components/.
- Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the documentation.
- Capability inventory: The skill performs file reads for auditing and file writes for persisting design patterns.
- Sanitization: No sanitization or validation logic for the ingested content is mentioned or described.
Audit Metadata