ClawHub
Back to skill

Security audit

technical writing

Security checks across malware telemetry and agentic risk

Overview

This is a coherent technical-writing skill with documentation templates, though users should edit a few risky example commands before copying them into real projects.

Install only if you are comfortable reviewing generated documentation before reuse. Replace the curl-to-shell installer with pinned, verified installation instructions, and treat runbook commands that restart services, change deployments, or alter production state as placeholders requiring explicit approval, impact checks, validation, and rollback planning.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The remediation section includes live-production actions such as restarting services, scaling deployments, failing over, and enabling maintenance mode without an explicit warning that these commands change system state and may cause downtime or secondary impact. In a runbook template, operators may copy these steps directly during an incident, increasing the risk of accidental disruption if preconditions, approvals, and verification steps are not called out.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The rollback section contains commands that alter the live deployment state, including undoing rollouts and setting a specific image, but does not warn that rollback itself is a production change with potential side effects such as schema/version mismatch or service interruption. During incident response, this omission can lead to unsafe rollback decisions being executed quickly without confirming compatibility or impact.

External Script Fetching

High
Category
Supply Chain
Content
brew install my-cli

# Binary
curl -fsSL https://get.my-cli.dev | sh
```

## Quick Start
Confidence
98% confidence
Finding
curl -fsSL https://get.my-cli.dev | sh

Chaining Abuse

High
Category
Tool Misuse
Content
brew install my-cli

# Binary
curl -fsSL https://get.my-cli.dev | sh
```

## Quick Start
Confidence
97% confidence
Finding
| sh

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal