ClawHub
Back to skill

Security audit

Video Toolbox

Security checks for vulnerabilities and agentic risk

Overview

This skill is a static reference helper that prints video-toolbox guidance and does not request credentials, network access, persistence, or system-changing authority.

Reasonable to install if you want quick local reference text for Video Toolbox. Expect generic guidance rather than a full video-processing tool, and note the command names are broad but the inspected behavior is non-mutating and offline.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description says the skill 'covers intro, guide, tips and more' and offers 'Quick lookup' reference help, but it does not clearly define when the skill should activate or what exact triggers are valid beyond generic command names. Phrases like 'tips' and 'guide' are broad and could overlap with ordinary requests unless invocation scope or exclusions are explicitly stated.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · scripts/script.sh (reported line 152)May include surrounding context.

sh
1. **Skipping planning**: Jumping in without understanding requirements
2. **Ignoring documentation**: Not recording decisions and changes
3. **Over-complicating**: Adding unnecessary complexity
4. **Skipping tests**: Deploying without verification
5. **Working in isolation**: Not seeking feedback or review

## How to Avoid Them