ClawHub
Back to skill

Security audit

中文自媒体内容工厂

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown content-writing skill for Chinese social media posts, with no executable code, credential use, persistence, or hidden system access.

Install this if you want Chinese social media content drafting and rewriting. Be aware it may activate on broad content-writing requests, and review any generated facts, platform-compliance claims, and human-sounding rewrites before publishing.

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)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The README advertises trigger phrases such as “写文案”, “内容创作”, “发小红书”, and “知乎回答”, which are common phrases in ordinary user conversation and not tightly scoped to explicit invocation intent. This can cause unintended activation of the skill in unrelated chats, leading to overbroad routing, surprise content generation, and possible interference with other safer or more appropriate skills.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The skill is explicitly framed as a Chinese-language content factory without indicating that language choice is configurable or user-driven. This can override user expectations, lead to unwanted language-constrained output, and reduce reliability when multilingual or non-Chinese requests are processed through the skill.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger list is broad and based on common phrases like '写文案', '内容创作', and '批量内容', which can cause the skill to activate in situations where the user did not explicitly request this specific tool. Over-broad activation increases the chance of misrouting user requests, unexpected behavior, and accidental application of the skill's content-generation behavior in unrelated contexts.

Static analysis

No suspicious patterns detected.