Openclaw Config Guard

Security checks across malware telemetry and agentic risk

Overview

This skill is a scoped OpenClaw configuration audit-and-repair helper with disclosed local file and CLI behavior.

Install only if you want an agent to inspect and possibly repair your local OpenClaw configuration. Review proposed config edits before applying them, keep the generated backup path, and require a successful post-change validation result before trusting the repair.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs the agent to read files, write configuration changes, inspect environment-dependent paths, and execute shell commands, but it declares no permissions. That mismatch weakens security review and policy enforcement because consumers may trust the manifest while the skill operationally performs higher-risk actions on local configuration files.

Tp4

High
Category
MCP Tool Poisoning
Confidence
87% confidence
Finding
The skill promises deterministic repair, rollback, and safe startup-blocking fixes, but the provided content appears to be procedural instructions without evidence that those protections are actually implemented. This creates a dangerous trust gap: operators may authorize automated config modification believing backups and rollback exist, when failures could instead leave the system misconfigured or unavailable.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal