ShellWard Security Guide

Security checks across malware telemetry and agentic risk

Overview

The available evidence points to a security-audit helper whose sensitive checks appear purpose-aligned, but the underlying skill file was not available for independent confirmation.

Install only if you intend to run local security-audit checks. Confirm the target scope before using it, avoid sharing raw secret values in prompts or outputs, and review any suggested changes before applying them.

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: 86% confidence
Finding: The skill activates on a very general condition ('when the user invokes this skill') without narrower trigger constraints or safety gating, which increases the chance it will be used in contexts where it inspects the system, reads sensitive files, or suggests risky hardening actions without clear scoping. In a security-focused skill, broad invocation is more dangerous because the described workflow includes checking system state and scanning locations like .env, .bashrc, and environment variables, which can expose sensitive data if invoked too freely.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal