xiaohongshu

Fail

Audited by Snyk on Mar 3, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.70). Most URLs are local API endpoints (localhost) which are not downloads, but the workflow directs you to clone/run scripts from an external, third‑party GitHub repo (peanut996/xiaohongshu-mcp) and to execute provided binaries/scripts (./xiaohongshu-login, ./start.sh), which is a common vector for malware and therefore represents a meaningful risk unless you audit the repository and its scripts first.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches user-generated Xiaohongshu posts, images and comments via a local MCP proxy (see SKILL.md "通过本地 MCP 服务器访问小红书内容" and the scripts/xhs_search.py calls to /api/v1/feeds/search and /api/v1/feeds/detail), and the workflow instructs the agent to read and summarize that third‑party content, which could contain instructions that influence subsequent actions.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Mar 3, 2026, 04:01 PM