ClawHub
Back to skill

Security audit

VeridicusScan MCP Analyst

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only security-scanning skill that coherently uses a VeridicusScan MCP bridge for user-selected URLs, files, prompts, and runtime-defense checks.

Install this only if you intend to use VeridicusScan MCP. Connect a trusted bridge, scan only the specific files, prompts, URLs, or runtime data you mean to share with it, and treat memory or selective-disclosure test inputs as sensitive.

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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The default prompt says to use this skill to scan a public URL, local file, or prompt and to use runtime-defense methods whenever tasks involve memory, selective disclosure, or tool approvals. This covers very broad classes of common requests and does not provide explicit trigger boundaries, exclusions, or negative examples, increasing the chance of unintended invocation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.