Back to skill

Security audit

XHS Copywriter Pro

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Xiaohongshu-style copywriting prompt with no code, data access, persistence, or hidden system behavior.

Install this only if you want Xiaohongshu-style promotional copy with a persuasive, intimate tone; review generated posts for authenticity, platform policy, and audience fit before publishing.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger description is broad enough to match many generic writing requests, which can cause the skill to activate outside its narrowly intended use case. Over-broad routing can hijack unrelated prompts, override user intent, and increase the chance that this skill’s persuasive social-media style is applied where it is inappropriate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

Forcing an 'extremely sincere, like a close girlfriend sharing' tone without user opt-in can manipulate the emotional framing of generated content and produce output misaligned with user expectations. While not a direct security exploit, it introduces persuasion and consent risks, especially when combined with marketing-oriented content targeting a specific demographic.

Content

No source excerpt is available for this finding.