ClawHub
Back to skill

Security audit

Post To Xhs

Security checks for vulnerabilities and agentic risk

Overview

This skill helps publish Xiaohongshu posts and requires a user preview and confirmation before posting.

Install this only if you want the agent to help prepare and publish Xiaohongshu posts. Check the preview carefully before confirming, especially media paths, visibility, scheduling, and whether the account is logged in through the expected Xiaohongshu integration.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger text includes very broad phrasing such as '帮我发一下' when context merely suggests Xiaohongshu, which can cause accidental or over-eager activation. In a skill that performs external posting, unintended activation is risky because it may collect content, prepare a post, or steer the user into publishing actions they did not explicitly request for this platform.

Static analysis

No suspicious patterns detected.