design-systems
Warn
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes a utility script,
assets/scripts/sync_upstream.py, designed to fetch and update design system files from the external repositorygithub.com/VoltAgent/awesome-design-md. This source is not recognized as a trusted organization. - [COMMAND_EXECUTION]: The
SKILL.mdfile contains instructions to execute shell commands usingbashandpython. These commands are used to generate JSON catalogs from the documentation and to launch a local HTTP server (assets/scripts/run_brand_preview.py) on port 17435 for browser-based visualization. - [PROMPT_INJECTION]: The skill defines a workflow where the agent reads and implements instructions from
DESIGN.mdfiles. Because these files contain design guidelines and behavioral constraints and can be updated from a remote repository, they represent a vector for indirect prompt injection. Malicious content in the upstream repository could potentially influence the agent's behavior.
Audit Metadata