Security audit

WeChat Browser Reader

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused browser-assisted extractor for WeChat articles, with a notable but manageable remote-debugging safety consideration.

Use this only with a temporary Chrome debugging profile on a trusted machine, avoid personal logged-in browser sessions, and close the debug browser when finished. The skill does not show hidden exfiltration or persistence, but remote browser control is inherently powerful.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill instructs use of a live Chrome instance with remote debugging enabled on port 9222 and browser automation against untrusted web content, but does not warn about the security implications. A remotely debuggable browser can expose cookies, session data, open tabs, and arbitrary browser control to local or network-accessible attackers, so users may unknowingly put sensitive browsing context at risk.

Static analysis

No suspicious patterns detected.