xiaohongshu-write

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches trending Xiaohongshu note data from the RedFox API at https://redfox.hk/story/api/xhs/search/search. This is a core part of its documented functionality to provide data-driven insights from the vendor's own platform.
  • [COMMAND_EXECUTION]: The provided Python script generates an HTML analysis report (e.g., keyword_热门数据.html) and saves it to the local filesystem. This is an intended feature to allow users to review the source data used for content generation.
  • [DATA_EXFILTRATION]: User-provided keywords and the REDFOX_API_KEY are sent to the RedFox API to retrieve relevant data. This represents normal operational data flow for the service.
  • [PROMPT_INJECTION]: The skill processes external data returned from the RedFox API, creating a surface for indirect prompt injection. However, this is inherent to the skill's purpose and the risk is considered negligible given the specific use case.
  • Ingestion points: API response processed in scripts/fetch_xhs_hot_articles.py
  • Boundary markers: Absent
  • Capability inventory: Local file system writes (HTML reports), web search via web_search tool
  • Sanitization: Title and description data is escaped when generating HTML reports to prevent XSS
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 07:51 PM
Security Audit — agent-trust-hub — xiaohongshu-write