xiaohongshu-crawler

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill transmits search keywords and an API key to the vendor's API at https://redfox.hk/story/api/xhs/crawl/work. This communication is a core requirement for the skill's content retrieval functionality and is directed at the author's official infrastructure.
  • [COMMAND_EXECUTION]: The skill involves the execution of local Python scripts, scripts/crawl_xhs.py and scripts/generate_report.py, to interact with the API and process data for the user.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: Data such as post titles, descriptions, and metadata are retrieved from the external Xiaohongshu API in scripts/crawl_xhs.py and passed into the agent's context.
  • Boundary markers: Results are displayed using structured markdown tables to isolate external data from the agent's instructions.
  • Capability inventory: The skill has the capability to write and save files locally via scripts/generate_report.py.
  • Sanitization: The report generation process utilizes HTML escaping and JSON serialization to ensure that external content is handled securely.
  • [DYNAMIC_EXECUTION]: The scripts/generate_report.py script creates HTML files by merging JSON data with a local template. This is done through standard string substitution and does not involve the execution of untrusted code at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 07:51 PM
Security Audit — agent-trust-hub — xiaohongshu-crawler