ClawHub
Back to skill

Security audit

微信文章完整流水线

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed WeChat article workflow that generates and reviews draft HTML without posting content or installing executable code.

Install only if you want a Chinese WeChat article workflow. Review the auto-run prompt carefully: choosing automatic mode lets it continue through drafting, AI-risk review, image research, revisions, and preview generation without repeated confirmations, but it does not publish to WeChat for you.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The instruction says writing quality must follow Chinese-language style rules, which imposes a specific language/locale requirement. The file does not present this as an explicit user choice or justified regional compliance constraint, so it constitutes a natural-language locale policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The default invocation prompt is broad enough to trigger a multi-step publishing pipeline from only a theme or brief, and it encourages automatic execution of downstream stages once the user opts in. In combination with implicit invocation, this weakens user intent validation and can cause the agent to perform substantial actions or delegated reviews without sufficiently specific user authorization.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.