ClawHub
Back to skill

Security audit

Cursor CLI Agent

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Cursor CLI guide, but it includes risky automation that installs remote code and automatically approves a workspace trust prompt.

Install only if you are comfortable with Cursor CLI acting on repositories where you run it. Prefer a verifiable installer or package-manager path, avoid `--force` unless changes are reviewed and reversible, and do not automate workspace trust for untrusted or newly downloaded projects.

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 (2)

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The README instructs users to execute a remotely fetched script directly via `curl ... | bash`, which removes the opportunity to inspect the installer before execution and creates a supply-chain risk if the server, transport, or script is compromised. In a developer tool skill, this is more dangerous because users are likely to copy-paste setup commands with elevated trust and may run them in privileged environments.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The tmux automation guide instructs sending `a` to trust the workspace automatically on first run, bypassing an important safety prompt without explaining the security implications. This can cause automated agents to approve untrusted repositories, potentially enabling execution or acceptance of malicious workspace-level configuration, rules, or tool behavior in a hostile codebase.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.