xiaohongshu-growth

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill manages authentication using session cookies (XIAOHONGSHU_COOKIE) within scripts/publish_to_draft.py. The implementation correctly uses environment variables to avoid credential hardcoding and targets official platform endpoints.
  • [DATA_EXFILTRATION]: Indirect Prompt Injection Surface.
  • Ingestion points: Data is ingested from external search results via the brave-search skill and competitor post data analyzed in scripts/analyze_competitor.py.
  • Boundary markers: The skill does not employ explicit delimiters or instruction-guarding techniques when processing these external data points.
  • Capability inventory: The skill can perform network POST requests to create or schedule drafts via scripts/publish_to_draft.py.
  • Sanitization: There is no evidence of input validation or content sanitization in the provided data-processing scripts.
  • [COMMAND_EXECUTION]: The skill uses local Python scripts to perform legitimate data processing and platform interaction tasks essential to its stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 07:57 AM
Security Audit — agent-trust-hub — xiaohongshu-growth