wechat-to-shopify-blog
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external content from WeChat URLs, which is a potential vector for indirect prompt injection. The instructions include specific mitigations, requiring the agent to wrap untrusted content in XML tags and explicitly instructing the model to treat the content as static text for translation only.
- [DATA_EXFILTRATION]: The skill manages Shopify credentials using environment variables. It follows security best practices by providing an initialization script that creates a local
.envfile and automatically adds it to.gitignoreto prevent accidental credential leakage to version control. - [COMMAND_EXECUTION]: The scripts interact with the official Shopify CLI to perform store operations. Command execution is handled via
execFilewith arguments derived from internal configuration and temporary files, minimizing the risk of command injection. - [EXTERNAL_DOWNLOADS]: The skill fetches article data and images from WeChat domains. This functionality is protected by a dedicated utility (
scripts/lib/public-fetch.mjs) that implements SSRF filtering, explicitly blocking requests to private, local, and loopback IP addresses.
Audit Metadata