Back to skill

Security audit

XHS Content Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese Xiaohongshu prompt generator with no evidence of hidden access, exfiltration, persistence, or destructive behavior.

Install this only if you want a Chinese-language Xiaohongshu content prompt helper. Expect it to create local text output files and to require sending the generated prompt to an AI assistant for final content.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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
Findings (8)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · generate.py (reported line 65)May include surrounding context.

python
if os.path.exists(prompt_path):
        with open(prompt_path, 'r', encoding='utf-8') as f:
            return f.read()
    return PROMPT_TEMPLATE

def generate_content(topic: str, hot_topic: str) -> str:
    """生成内容"""

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · generate.py (reported line 71)May include surrounding context.

python
"""生成内容"""
    prompt = load_prompt()
    prompt = prompt.format(topic=topic, hot_topic=hot_topic)
    return prompt

def main():
    parser = argparse.ArgumentParser(description='小红书爆款内容生成器')

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The module docstring says this is a 'content generator' that generates viral titles and content outlines. In practice, generate_content only formats a prompt string, and the CLI explicitly tells the user to send that prompt to an AI assistant to get the actual result, so the documentation contradicts the real behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The embedded natural-language prompt is entirely in Chinese and explicitly instructs the model to produce content in a specific Xiaohongshu style, with no option for the user to choose another language or locale. This is a language policy concern because the skill imposes a fixed language/locale behavior rather than offering user choice or documenting a justified regional restriction.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The function is documented as '生成内容' ('generate content'), but its implementation only loads a template and interpolates topic and hot_topic. No content generation occurs; it returns instructions intended for another model to use.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Line L01 instructs the model in Chinese and defines it as a Xiaohongshu content creator, while the rest of the prompt consistently assumes Chinese-language output for the generated content. This is a natural-language locale constraint with no user opt-in or explicit justification, which can violate language/locale policy requirements.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language instructions and examples are presented only in Chinese, which can amount to forcing a specific language without user opt-in. The file does not state that the skill is region-specific or offer an alternative language/localization choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description states the skill is a '小红书内容生成助手', implying Chinese-language/content-platform-specific operation, but the manifest does not indicate any user opt-in or configurable language/locale choice. This can violate language/locale policy when a skill appears to assume a specific language by default without documenting that constraint.

Content

No source excerpt is available for this finding.