write-xiaohongshu
Warn
Audited by Snyk on Mar 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly requires using the Xiaohongshu MCP get_specified_post tool to fetch Top10 public Xiaohongshu image posts and their comments (user-generated content) and then analyzes that content to drive writing, decisions, and publishing, which exposes the agent to untrusted third‑party input.
Audit Metadata