vite-webcontainer-developer
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute specific scripts located within the project repository, such as
node scripts/recover-and-start.jsandnode scripts/extractFilesFromMarkdown.ts. While these are intended as recovery tools, they allow for the execution of arbitrary code defined within the user's project workspace. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to parse and act upon external data, such as build error messages, stack traces, and project source files, without explicit sanitization.
- Ingestion points: Build logs, error messages, and existing project files (e.g.,
package.json,index.html) analyzed in the instructions. - Boundary markers: The instructions do not define clear boundaries or delimiters to isolate external data from the agent's logic.
- Capability inventory: The agent has the ability to read and write project files and execute shell commands (
npm,pnpm,node). - Sanitization: No sanitization or validation of external input is required by the instructions.
- [DYNAMIC_EXECUTION]: The skill automates the creation and modification of project files (e.g.,
vite.config.js,src/lib/utils.ts) which are then executed as part of the Vite development server lifecycle.
Audit Metadata