Back to skill

Security audit

Proxmox MCP for OpenClaw

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says, but it installs and registers a downloaded executable that will receive Proxmox credentials without a strong independent trust check.

Install only if you trust the GitHub release publisher and are comfortable giving the registered MCP your Proxmox token. Use a dedicated least-privilege Proxmox token, review the upstream release and checksum yourself, prefer a disposable test environment first, and rotate the token if command-line telemetry or process monitoring may have captured it.

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (3)

T03 · Remote Payload Retrieval and Execution

Error
Location
scripts/installer.mjs:20
Finding

Untrusted Remote Executable Downloaded and Registered for Execution

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/installer.mjs:266
Finding

Proxmox Credentials Exposed in Child-Process Command-Line Arguments

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/installer.mjs:134
Finding

Unbounded Download Buffering and Archive Extraction Enable Resource Exhaustion

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

This code installs files into a user-specified directory, downloads release artifacts over the network, and invokes the external openclaw command to register the MCP using environment-provided credentials. There is no confirmation prompt, print/log statement, or explanatory comment/docstring in this file disclosing these safety-relevant actions to the user.

Content

No source excerpt is available for this finding.