ClawHub
Back to skill

Security audit

Opencli

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a legitimate OpenCLI bridge, but it delegates broad local command and logged-in browser-session authority with limited user-control guidance.

Install only if you intend to let the agent route tasks through a local OpenCLI install. Review commands before execution, avoid sensitive browser profiles or accounts unless necessary, and treat external CLI passthrough commands as capable of reading or changing local, repository, cloud, or account state.

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
91% confidence
Finding
The file documents browser-backed commands that may operate through a logged-in browser session, but it does not warn that these actions can access session-bound data, personalized results, or account context. In an agent skill, this omission can cause operators or downstream agents to run commands against sensitive accounts without understanding the privacy and account-exposure risk.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.