ClawHub
Back to skill

Security audit

send-to-me

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says by sending WeCom messages, but its broad trigger wording and default send-to-all recipient create a real risk of accidental organization-wide disclosure or spam.

Review before installing. Use only with a limited-permission WeCom app, change the default recipient away from @all, and require explicit confirmation of both message content and recipients before sending. Do not use this for sensitive reports unless recipient scoping is enforced.

SkillSpector

By NVIDIA
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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill documentation shows it uses environment variables and network access to send WeCom messages, yet no permissions are declared. This creates a transparency and policy-enforcement gap: an agent or platform may invoke a skill with capabilities the user did not explicitly approve, enabling outbound data transmission and secret use without clear consent.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger description is extremely broad, covering essentially any scenario involving messages, reports, notifications, or alerts. Such overbroad matching can cause unintended invocation, which is risky here because the skill performs outbound messaging and could leak sensitive content to enterprise chat recipients if activated by ordinary conversation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.