Back to skill

Security audit

Xiaohongshu Topic Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only content ideation skill for Xiaohongshu topics with no hidden execution, persistence, or privileged access.

Install this if you want help brainstorming Xiaohongshu/Rednote content. Be aware that the default template is Chinese and platform-specific, and ask explicitly if you want another language or a non-Xiaohongshu format.

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
  • 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The output template is fully specified in Chinese, including fixed section headings like '本轮小红书选题建议' and field labels, but the skill does not state that language should match user preference or ask for opt-in. This can violate language/locale policy by forcing a specific language without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instructions are entirely in Chinese and direct the model to generate Xiaohongshu topics, which implicitly constrains the interaction to a specific language and locale. The file does not offer any opt-in, alternative language choice, or justification that this skill is intentionally region-specific for compliance or similar reasons.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The description says to use the skill when the user wants 'content angles,' 'post hooks,' or to turn 'a theme into publishable Xiaohongshu topic candidates.' While Xiaohongshu is mentioned, several trigger examples are generic content-ideation phrases and there are no explicit negative examples clarifying when a general brainstorming request should not invoke this skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.