ClawHub
Back to skill

Security audit

XiaoHongShu Search MCP

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow, disclosed connector for searching XiaoHongShu through whatson.red and does not include hidden code, persistence, or destructive behavior.

Install only if you are comfortable giving the skill access to a whatson.red Agent API key and having your search queries billed through that service. Treat returned blog content as a draft, and review costs/credit usage before running large searches.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Safety Notes

- Do not ask the user for Browserless, proxy, cookie, or deployment secrets; this skill only uses the hosted whatson.red MCP endpoint.
- Do not attempt to scrape XiaoHongShu directly from this skill.
- Do not publish posts when `include_blog` is true; the returned blog payload is only a draft.
Confidence
80% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.