vite-react

Warn

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads a full project template from an external GitHub repository (https://github.com/Eng0AI/vite-react-template.git) which is not associated with the skill author or a trusted organization.
  • [COMMAND_EXECUTION]: Instructions guide the agent to run npm install and npm run build on the cloned files. This automatically executes scripts defined in the external repository's package.json (such as postinstall or the build script itself), providing a path for remote code execution from an unverified source.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing and executing code from an external source without verification.
  • Ingestion points: Clones content from https://github.com/Eng0AI/vite-react-template.git into the local environment.
  • Boundary markers: None; the agent is instructed to treat the external content as a trusted project template.
  • Capability inventory: Includes shell command execution (npm, git, vercel, netlify) and file system operations.
  • Sanitization: None; the skill does not validate the integrity or safety of the downloaded repository before execution.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 23, 2026, 06:06 PM