linkfox-xiyou-dongcha
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFEDATA_EXFILTRATION
Full Analysis
- [SAFE]: The skill's code and instructions are consistent with its stated purpose of providing Amazon ASIN and keyword research. No malicious patterns such as persistence, privilege escalation, or obfuscation were found.
- [EXTERNAL_DOWNLOADS]: The skill performs legitimate network requests to vendor-controlled domains including
tool-gateway.linkfox.comandskill-api.linkfox.com. It also references a vendor-hosted skill package atagent-files.linkfox.comfor onboarding purposes. These destinations are consistent with the vendor's infrastructure. - [COMMAND_EXECUTION]: The skill executes a local Python script (
scripts/xiyou.py) to process query parameters and communicate with the remote API. This is a standard execution pattern for this type of skill. - [CREDENTIALS_UNSAFE]: The skill requires multiple API keys (
LINKFOXAGENT_API_KEY,XIYOU_CLIENT_ID,XIYOU_CLIENT_SECRET). The documentation correctly instructs the user to provide these via environment variables rather than hardcoding them, which follows security best practices. - [DATA_EXFILTRATION]: As part of its core functionality, the skill transmits Amazon ASINs and search keywords to the LinkFox gateway. This data transmission is intended and necessary for the analytical services provided.
Audit Metadata