wechatpay-payment-integration
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches and synchronizes documentation from WeChat Pay's official resource domain (
wx.gtimg.com) to a local assets directory. The process is managed by a Python script that downloads a ZIP archive and extracts it to update the skill's knowledge base. - [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local Python synchronization script (
wechatpay-docs-sync.py) to maintain documentation. Additionally, it generates formatted shell and PowerShell commands for the user to execute locally for extracting certificate information and generating APIv3 signatures. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of processing external data.
- Ingestion points: The agent retrieves and processes external documentation files from the
assets/微信支付官网文档/directory as part of its RAG (Retrieval-Augmented Generation) workflow. - Boundary markers: The instructions include explicit directives to the agent to rely solely on the provided documentation and not to invent answers, though it lacks strict data-delimiters for the retrieved content.
- Capability inventory: The skill has the capability to execute local scripts and generate system commands for debugging and troubleshooting.
- Sanitization: No active sanitization or filtering of the content within the synchronized documentation files was observed.
Audit Metadata