ClawHub
Back to skill

Security audit

Fox Xiaohongshu Publish

Security checks for vulnerabilities and agentic risk

Overview

The skill is a simple Xiaohongshu publishing helper, but it can route drafting requests into a live posting workflow without a clear final user confirmation.

Review this before installing if you only want drafting help. Use it only when you intend to publish to Xiaohongshu, and require the agent to show the exact title/body and ask for explicit confirmation before clicking Publish.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad enough to activate this skill for generic requests like '写一篇小红书', which could cause the agent to invoke a real publishing workflow when the user may only want drafting help rather than posting. In the context of a skill that performs external publication, overbroad routing increases the risk of unintended content posting or the agent selecting this skill instead of a safer, non-posting writing skill.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill describes a workflow that ends with clicking the external platform's '发布' button, but it does not prominently warn that using the skill will create a live post on Xiaohongshu. Because this is an external side-effecting action, lack of clear disclosure and confirmation can lead to accidental publication, reputational harm, or leakage of sensitive or draft content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.