ClawHub
Back to skill

Security audit

OpenClaw VLN Planner

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed robot navigation planner with real privacy and safety cautions, but the artifacts are coherent and do not show hidden or malicious behavior.

Use this only with a trusted multimodal gateway and assume robot camera frames and navigation context may leave the device. Keep dry_run enabled during testing, add human supervision and independent safety controls before connecting a real robot, store the API key outside plaintext config where possible, and pin/audit the Python dependencies before deployment.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill instructs the runtime to read local configuration files and use an OpenAI-compatible multimodal gateway with a base URL and API key, which implies file-read and network capabilities. Because these capabilities are not explicitly declared as permissions, the host may expose more access than reviewers or operators expect, creating a trust and containment gap that could lead to unintended data access or outbound transmission of images, instructions, and robot state.

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests>=2.31.0
PyYAML>=6.0.1
Confidence
94% confidence
Finding
requests>=2.31.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests>=2.31.0
PyYAML>=6.0.1
Confidence
95% confidence
Finding
PyYAML>=6.0.1

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High
Category
Supply Chain
Confidence
82% confidence
Finding
requests

Known Vulnerable Dependency: PyYAML — 8 advisory(ies): CVE-2019-20477 (Deserialization of Untrusted Data in PyYAML); CVE-2020-1747 (Improper Input Validation in PyYAML); CVE-2020-14343 (Improper Input Validation in PyYAML) +5 more

Critical
Category
Supply Chain
Confidence
93% confidence
Finding
PyYAML

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal