ClawHub
Back to skill

Security audit

General Software Automation

Security checks for vulnerabilities and agentic risk

Overview

This is a broad local automation skill that can affect files and the active desktop, but its reviewed behavior is disclosed and aligned with that purpose.

Install only if you need broad local desktop and file automation. Review any JSON GUI script before running it, keep the intended application active, avoid typing secrets through the helper because it logs a text preview, use batch rename preview mode first, and require explicit approval before any admin-level install, registry, service, log-collection, or screenshot task.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill advertises destructive or high-impact operations such as batch rename, search/replace, install/uninstall, registry changes, environment variable management, and service control without requiring confirmation or warning about irreversible effects. In an automation context, this increases the chance of accidental system damage, data loss, or service disruption at scale.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill includes system information collection, log aggregation, and screenshot capture without any privacy notice, data minimization guidance, or consent requirement. These features can expose credentials, tokens, personal data, internal documents, and other sensitive information if invoked broadly or stored insecurely.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The script can take screenshots and perform arbitrary GUI clicks, typing, hotkeys, scrolling, and drag operations from command-line input or a JSON script, but it provides no confirmation prompt, dry-run mode, scope restriction, or warning about interacting with sensitive applications or data. In this skill context, GUI automation is expected functionality, so this is not inherently malicious, but the absence of guardrails increases the risk of accidental data exposure, destructive actions, or unintended interaction with privileged windows.

Static analysis

No suspicious patterns detected.