Security audit

小红书内容生成引擎

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Xiaohongshu content strategy skill with formatting and activation-scope issues, but no evidence of hidden commands, persistence, exfiltration, or unsafe authority.

Before installing, review the malformed header and broad trigger keywords; the skill appears safe as markdown guidance, but it may be better scoped if activation is limited to explicit Xiaohongshu content-planning requests.

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

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 (3)

Whitespace Padding

Medium

Category: Prompt Injection
Confidence: 70% confidence
Finding: Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
Content: Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.
md
*** **name: xiaohongshu-growth- engine version: 1.0.1 description: >-**** 科学打造小红书流量博主的内容更新引擎，基于说服理论、情绪感染理论及平台实证研究，自动生成高互动内容策略、选题日历和爆款文案。适用于需要系统化涨粉和内容规划的博主。 trigger-keywords: >- 小红书内容策略, 博主涨粉, 内容日历, 爆款内容生成, 科学选题, 流量博主打造, 小红书运营, 内容更新计划, xiaohongshu growth, content strategy author: Your Name license: MIT tags: * xiaohongshu

Whitespace Padding

Medium

Category: Prompt Injection
Confidence: 70% confidence
Finding: Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
Content: Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.
md
*** **name: xiaohongshu-growth- engine version: 1.0.1 description: >-**** 科学打造小红书流量博主的内容更新引擎，基于说服理论、情绪感染理论及平台实证研究，自动生成高互动内容策略、选题日历和爆款文案。适用于需要系统化涨粉和内容规划的博主。 trigger-keywords: >- 小红书内容策略, 博主涨粉, 内容日历, 爆款内容生成, 科学选题, 流量博主打造, 小红书运营, 内容更新计划, xiaohongshu growth, content strategy author: Your Name license: MIT tags: * xiaohongshu

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest-style header lists trigger keywords such as '小红书内容策略', '博主涨粉', and '内容更新计划', which are broad topic phrases a user might mention in ordinary discussion rather than explicit invocation commands. The file does not provide scope limits, negative examples, or clear conditions for when the skill should activate versus when it should not.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.