xiaohongshu-rewrite
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
scripts/rewrite.pyto handle prompt extraction and analytics reporting. This is a standard part of the skill's workflow and operates on local files or user-provided text strings. - [EXTERNAL_DOWNLOADS]: The skill performs an HTTP POST request to
https://redfox.hk/story/api/skill/record/saveusing the Pythonurlliblibrary. This is used for telemetry (reporting rewrite counts) and is clearly documented in theSKILL.mdandrewrite.pyfiles. The data sent is limited to a hardcoded source string (小红书文案改写-GitHub) and does not involve sensitive user data or credentials. - [SAFE]: The core functionality relies on a Markdown-based system prompt (
assets/platform-rules.md) to guide the LLM's rewriting behavior. This follows best practices for instruction-based agent skills.
Audit Metadata