Back to skill

Security audit

创建微信视频号合集_无限

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly does one account-changing task: it guides an agent through creating a WeChat Channels video collection.

Install only if you want an agent to operate your logged-in WeChat Channels backend and create collections. Before use, provide the exact collection title and confirm the final Create action to avoid unwanted account clutter.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger phrases are generic and repeated, with no clear exclusion boundaries or user-confirmation gate before executing a write-capable workflow. In an agent environment, this increases the chance of accidental invocation from ordinary conversation, which could lead to unintended navigation and account-affecting actions in the user's WeChat Channels backend.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill performs a persistent write action—creating a new collection in the user's account—but does not clearly warn that it will modify account state or require explicit user approval at the point of execution. This is dangerous because an automatically invoked browser agent could create unwanted collections, causing account clutter, operational mistakes, or abuse if triggered unintentionally.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.