next-theme-design
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions and test files (
tests/test_design_package.py,tests/test_skill_package.py) involve the execution of the skill's own Python and Node.js scripts via theBashtool andsubprocess.runcalls.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external websites, which serves as a potential injection vector.\n - Ingestion points:
scripts/capture-page.jsextracts text, link destinations, and accessible names from target URLs.\n - Boundary markers: The captured data is stored in structured JSON and Markdown files within a handoff package.\n
- Capability inventory: The agent has access to
Write,Edit, andBashtools to manage the package files.\n - Sanitization: The Python scripts use standard JSON libraries for data serialization.\n- [EXTERNAL_DOWNLOADS]: The skill provides instructions in
SKILL.mdandREADME.mdto install related tools from theNextCommerceCoorganization on GitHub usingnpxand the./skills.shinstaller.
Audit Metadata