ClawHub
Back to skill

Security audit

WhatsApp Local Endpoints Router

Security checks across malware telemetry and agentic risk

Overview

This skill appears purpose-built to route WhatsApp content to local services, but its broad triggering and raw localhost response relay need user review before installation.

Install only if you intentionally want WhatsApp content routed into a local service on port 8080. Use it with a trusted local backend, avoid sending sensitive chats or QR/images unless needed, require explicit user intent before forwarding attachments, and do not expose backend errors or secrets through raw responses.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill instructs the agent to execute a shell script, but the metadata shown does not declare corresponding permissions. That creates a capability/visibility mismatch: users or platform controls may not realize the skill can invoke local code and networked localhost services, which increases the risk of unintended command execution paths and weakens governance.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The invocation description is broad enough to match ordinary WhatsApp text or symbols, which could cause the skill to trigger on routine conversations without meaningful user intent. In this skill's context, that means arbitrary message content may be forwarded to local HTTP endpoints and processed automatically, expanding the attack surface and enabling accidental data transmission.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill description does not warn that WhatsApp text or images will be transmitted to localhost endpoints and that backend responses may be returned directly to the user. This missing disclosure is dangerous because users may unknowingly send sensitive chat content or QR data into a local processing pipeline whose behavior and data handling are opaque.

Ssd 3

High
Confidence
98% confidence
Finding
The skill explicitly requires returning arbitrary backend JSON and even raw error bodies directly to the user, creating a direct exfiltration channel from local services to the chat. If the localhost service exposes secrets, stack traces, internal paths, tokens, or other sensitive data, the skill will faithfully relay that material to the user with no filtering or redaction.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal