xiaohongshu-similar-account
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute a local Python script (
scripts/xiaohongshu_account_recommender.py) to process user requests and generate reports. - [EXTERNAL_DOWNLOADS]: The Python script performs POST requests to
https://redfox.hk/story/api/xhsUser/querySimilarAccountsto retrieve benchmark data. As this is the core service provided by the skill author (redfox-data), and the domain is the official vendor site, this is identified as expected behavior. - [DATA_EXPOSURE]: The skill correctly handles authentication by requiring a
REDFOX_API_KEYvia environment variables rather than hardcoding credentials, which is a standard security best practice. - [REMOTE_CODE_EXECUTION]: No patterns were detected involving the piping of remote scripts into shell interpreters or dynamic execution of untrusted remote code.
- [PROMPT_INJECTION]: The instructions do not contain markers intended to bypass safety filters or override system constraints; they focus purely on task execution and data formatting.
Audit Metadata