wxa-skills-validate
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes Node.js scripts (execute.mjs, render.mjs, validate.mjs) to execute the WeChat DevTools CLI via child_process.spawn. This functionality is essential for performing the skill's stated purpose of local validation, compilation checks, and component rendering.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface as it is designed to ingest and process code from local projects. 1. Ingestion points: Reads local project files including app.json, mcp.json, and source files (.js, .wxml, .wxss) in scripts/validate.mjs. 2. Boundary markers: Data processing is governed by regex-based validation and structured JSON parsing, although no specific delimiters are used to warn the agent about embedded instructions in the source code. 3. Capability inventory: The skill has the capability to modify the local file system to repair errors and to execute shell commands through the official WeChat DevTools CLI. 4. Sanitization: Command arguments are escaped using the shellQuote utility in scripts/lib.mjs to mitigate potential command injection.
- [SAFE]: The skill is a specialized development tool for the WeChat Mini Program ecosystem. It follows standard developer workflows, utilizes official vendor tools, and performs actions that are strictly aligned with its primary purpose of ensuring component quality.
Audit Metadata