ClawHub
Back to skill

Security audit

Notify with Pushover

Security checks across malware telemetry and agentic risk

Overview

This skill transparently sends user-provided push notifications through Pushover and does not show hidden or unrelated behavior.

Install this only if you are comfortable sending notification contents and optional URLs to Pushover. Prefer environment variables or a secret store for the app token and user key, avoid passing real credentials directly on shared command lines, and review automated alert workflows to prevent spam or accidental disclosure of sensitive message text.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs use of environment variables for secrets and invokes a Node script that makes outbound API calls, but the skill declares no corresponding permissions. This creates a permission-model gap: an agent or reviewer may underestimate the skill's ability to access credentials and send network traffic, which can enable unintended data disclosure or unauthorized external communications.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/pushover_send.js:40