ClawHub
Back to skill

Security audit

微信公众号文章排版器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a WeChat article HTML formatter with no hidden execution, credential use, persistence, or destructive behavior.

Install this if you want help producing WeChat-compatible article HTML. Before using it, check where the agent will write the output file and confirm any user-specified path to avoid accidental overwrites.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger conditions are broad enough to capture generic article-writing or Markdown-conversion requests, which can cause the skill to activate outside its intended WeChat-specific scope. Over-broad activation increases the chance of inappropriate tool behavior, unexpected HTML/file-generation actions, and routing user requests into a specialized formatter when a general writing response would be safer.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs writing output to article.html or a user-specified path without requiring confirmation, clarifying overwrite behavior, or constraining permissible destinations. If the agent follows this automatically, it could overwrite existing files or create files in unintended locations, especially when paired with ambiguous or adversarial path input.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The HTML root declares lang="zh-CN", and the visible template content is written entirely in Chinese, which imposes a specific language/locale on all uses of the template. The file does not indicate that the locale is optional, configurable, or limited to a justified region-specific use case.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file is entirely written in Chinese and presents all guidance, labels, and examples only in that language. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is explicitly justified, which is not stated here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.