ClawHub
Back to skill

Security audit

Weixinclaw Proactive Push

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says, but it can send WeChat messages and files using local bot credentials without an explicit confirmation boundary.

Install only if you intend this skill to let an agent send WeChat messages and media to the boss contact configured in WorkBuddy. Review the local settings and cursor files it reads, avoid using it for confidential content unless you are comfortable sending that content through Tencent/WeChat infrastructure, and require your agent workflow to preview and confirm each outbound message before running send.js.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill clearly instructs outbound network use to Tencent/WeChat endpoints, yet no declared permissions are present. In an agent environment, undeclared network capability is dangerous because it can enable silent data exfiltration or unreviewed message delivery to external recipients using locally stored credentials.

Vague Triggers

Medium
Confidence
81% confidence
Finding
The trigger phrases are broad and loosely bounded, so the skill may activate on ambiguous requests and send unsolicited WeChat messages to a boss/contact. In this context, mis-triggering is more dangerous because the skill can perform external communication using sensitive local bot credentials and a predefined recipient.

Vague Triggers

Low
Confidence
74% confidence
Finding
The 'when to use' section lacks clear exclusion conditions, which increases the chance an agent invokes the skill for loosely related messaging tasks. Because the skill performs outbound delivery to a real person over WeChat, accidental activation can leak sensitive content or create unauthorized communications.

Static analysis

No suspicious patterns detected.