Security audit

Wechat Article Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This is a simple WeChat article optimization prompt skill with no executable code, install actions, persistence, or sensitive access.

Safe to install as a content-writing helper. Be aware that broad prompts like asking for a cover image or best publishing time may invoke it unintentionally, so use it when you specifically want WeChat article optimization advice.

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

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 (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The invocation examples are generic natural-language requests like '推荐一个合适的封面图' and '什么时候发布阅读最高', which overlap with ordinary user prompts and can cause the platform to trigger this skill unintentionally. This broad matching increases the chance of prompt hijacking or misrouting benign conversations into the skill, especially when article content is pasted verbatim and may contain adversarial instructions.
Content: No source excerpt is available for this finding.