ClawHub
Back to skill

Security audit

Wander Monitor

Security checks across malware telemetry and agentic risk

Overview

This skill has a reasonable CI-monitoring purpose, but it tells agents to automatically start background local scripts after pushes without a fresh confirmation step.

Install only if you trust the Wander repository and are comfortable with agents starting background CI monitors after pushes. Prefer asking the agent to confirm the exact command, inspect any repo-local watch wrapper before it runs, and pin or review the Wander checkout you use.

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 (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs the agent to automatically launch an external background script after every qualifying `git push` unless the user opts out, without requiring explicit informed consent at the moment of execution. This creates an autonomy and transparency issue: the agent may initiate networked monitoring behavior and spawn background processes the user did not clearly request, which is especially risky because it relies on local wrappers or `$WANDER_HOME` scripts that could vary by environment.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.