Back to skill

Security audit

WeChat Mini Program Automation SDK

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent documentation-only skill for WeChat Mini Program UI automation, with powerful testing APIs that users should handle carefully.

Install only if you are comfortable giving an agent WeChat DevTools automation access for the selected project. Treat login tickets and screenshots as sensitive, avoid logging or committing them, and use evaluate/exposeFunction only against trusted test environments or test accounts.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill describes retrieving, setting, and refreshing login tickets without labeling them as sensitive credentials or warning about account takeover risk if exposed. In automation contexts, such tokens are highly sensitive and could enable unauthorized access or persistent session abuse if logged, stored insecurely, or passed to other tools.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 235)May include surrounding context.

md
| [references/api.md](references/api.md) | Complete API parameter tables and examples |

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The skill documentation advertises taking screenshots and saving them to a local file, which can capture sensitive UI content or user data. In this markdown file, there is no accompanying warning about the privacy implications or careful handling of captured data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly documents code evaluation against the running mini program and access to global application data without any warning about trust boundaries, secrets exposure, or test-environment restrictions. In an agent skill context, this can normalize runtime code injection and data extraction, which could be used to read sensitive state or alter application behavior during automated workflows.

Content

No source excerpt is available for this finding.