ClawHub
Back to skill

Security audit

shorts-generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Markdown-only short-form video generation guide with expected references to URLs and media providers, but no hidden execution, persistence, or destructive behavior.

Installers should treat this as a content-generation helper, not an autonomous production pipeline. Avoid giving it private URLs, confidential scripts, unreleased media, or copyrighted assets unless you are comfortable with the external providers you choose to use.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description is overly broad and can cause the agent to invoke this skill in many loosely related contexts, including when external URL ingestion, asset sourcing, or content generation may not be appropriate. In a skill that can pull from URLs and third-party providers, unclear trigger boundaries increase the chance of unintended data sharing, unsafe automation, or misuse without explicit user intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill describes workflows that accept URLs and use external asset, music, and voice providers but does not warn users that content may be fetched from external sources or sent to third parties. In this context, missing disclosure is risky because users may unknowingly expose sensitive URLs, copyrighted material, or private text to outside services during automated video generation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.