ClawHub
Back to skill

Security audit

NEXO Desktop Runtime

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent NEXO Desktop runtime installer, but it asks users to execute an unpinned npm package that can install a persistent local MCP runtime.

Install only if you trust the `nexo-brain` npm package and publisher. Prefer an exact reviewed version, verify what creates `~/.nexo/server.py`, and be aware that the runtime maintains local memory and can run through the OpenClaw gateway across sessions.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T08 · Insecure Dependencies

Error
Location
SKILL.md:15
Finding

Unpinned Third-Party Package Is Downloaded and Executed

Content
View full analysis
Remediation
View remediation
`, rather than resolving the latest release. 2. Record and verify the package's registry integrity digest before execution. Use a lockfile or equivalent reproducible dependency manifest where possible. 3. Prefer installing from a controlled artifact repository or verified release archive with published checksums and signature validation. 4. Disable or separately inspect npm lifecycle scripts during installation when they are not required. 5. Document every file the installer creates, particularly `~/.nexo/server.py`, and verify its cryptographic hash against the audited release before registering it as an MCP server. 6. Run installation and the MCP server with the minimum required privileges, using filesystem and network isolation where practical. 7. Establish an update-review process so new package versions are not automatically trusted merely because the Skill documentation remains unchanged. ]]>

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The setup instructions tell users to run npx nexo-brain without pinning a specific version, which can fetch and execute whatever version is current at install time. Because this skill is a runtime core with memory, watchdog, and MCP/server capabilities, a compromised or malicious package update could gain broad local code-execution and persistence-related access on the user's machine.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.