ClawHub
Back to skill

Security audit

Xiaohongshu

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Xiaohongshu content-writing guide with a local text-checking script and no evidence of hidden access, persistence, or data exfiltration.

This appears safe to install for Xiaohongshu content drafting and pre-publish review. Treat the compliance checker as a limited local heuristic, not a guarantee of platform approval or legal compliance, and review generated marketing claims before posting.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The description presents a broader skill with content-strategy guidance, compliance self-checking, and diagnostic analysis. The code chunk only implements the compliance checker portion, using local regex/keyword rules on text input. It does not generate or evaluate titles/covers/body structure/tags beyond basic text checks, and it does not analyze note metrics or diagnose where performance issues occur. So the code behavior is narrower than the declared purpose, making the overall description inaccurate for this supplied code chunk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.