miniprogram-development
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of various CLI tools to perform project management and development tasks.
- Suggests the execution of
wechatidefor project management, debugging, and CloudBase operations. - Recommends configuring and executing
@cloudbase/cloudbase-mcp@latestvianpxto access extended CloudBase functionality. - Uses
miniprogram-cias a fallback mechanism for project previews, uploads, and NPM builds. - [EXTERNAL_DOWNLOADS]: The skill directs users to fetch resources from official and well-known service providers.
- References the official WeChat developer domain for downloading WeChat Developer Tools (Nightly):
https://developers.weixin.qq.com/miniprogram/dev/devtools/nightly_backup.html. - Instructs the fetching of the
@cloudbase/cloudbase-mcppackage from the NPM registry. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a typical attack surface for indirect prompt injection due to its role in processing external project data.
- Ingestion points: The skill reads project configuration files such as
project.config.jsonand various code assets (JavaScript, WXML, WXSS, JSON) to guide the agent's actions. It also consumes output from thewechatideCLI tools. - Boundary markers: No specific boundary markers or system instructions were found that explicitly warn the agent to disregard instructions potentially embedded within these project files.
- Capability inventory: The skill has the ability to execute shell commands (
wechatide,npx), write files (generating project skeletons and components), and perform network operations through the integrated tools. - Sanitization: There is no explicit evidence of sanitization or validation of the content read from project configuration files before it is processed by the agent to construct commands or prompts.
Audit Metadata