ClawHub
Back to skill

Security audit

pushplus

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed PushPlus notification helper, with expected external sending behavior and reasonable safeguards for confirmation and credential handling.

Install only if you intend to send selected notification content through PushPlus. Do not send secrets, raw logs, credentials, or personal data unless you deliberately accept that disclosure, and review any Open API account-management action before confirming it.

SkillSpector

By NVIDIA
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 (3)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The README clearly states that the skill sends notifications through the PushPlus HTTP API, which necessarily transmits message content and authentication material to a third-party service, but it does not prominently warn users about that disclosure. This can cause users or agents to forward sensitive logs, secrets, or personal data off-host without informed consent, especially in automation contexts.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The usage text says the agent will automatically use the skill when asked to send notifications, but it does not warn that the requested content will be delivered externally through PushPlus and potentially to email, webhook, SMS, or chat channels. In an agent setting, this increases the risk of inadvertent exfiltration of sensitive runtime output, logs, or user data through normal-language requests.

External Transmission

Medium
Category
Data Exfiltration
Content
An [OpenClaw](https://clawhub.ai) agent skill that enables AI agents to send push notifications via [PushPlus](https://www.pushplus.plus) HTTP API (消息接口 V1.16) to WeChat, ClawBot, email, webhook, SMS, App, and more — with progressive disclosure of Open API (V1.15) for result lookup and account management.

**Zero dependencies** — works with any agent that has Shell/curl access. No MCP server or extra packages required.

## Features
Confidence
95% confidence
Finding
curl access. No MCP server or extra packages required. ## Features - **Direct HTTP API** — No extra dependencies, just curl - **9 channels**: WeChat, App, extension, webhook, ClawBot, enterprise WeC

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.