OpenClaw MCP Debugger

Security checks across malware telemetry and agentic risk

Overview

This MCP troubleshooting skill appears purpose-aligned, but its broad all-target diagnostics and automatic repair/restart behavior need review before use.

Install only if you are comfortable with a skill that may inspect all configured MCP targets and perform repair actions. Prefer using it with explicit server names or dry-run style requests, and avoid automatic fixes on sensitive or production-linked MCP integrations unless you have reviewed what will be restarted or changed.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (2)

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The skill markets itself as a universal MCP diagnostic tool and shows a `--all` invocation without defining scope limits, target boundaries, or exclusions. In an agentic environment, this ambiguity can cause the skill to enumerate, probe, or affect every reachable MCP server or adapter, increasing the chance of unintended access, disruption, or misuse beyond the operator’s intent.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill advertises 'Auto-Fixer' behavior that automatically restarts crashed MCP servers and repair paths, but provides no warning about service interruption, state loss, or impact on dependent tools. In the context of developer infrastructure and local MCP servers, automatic restarts can disrupt active sessions, corrupt transient state, or restart sensitive integrations without informed consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal