ClawHub
Back to skill

Security audit

Media Gen Vision Video

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed media workflow guide for image, screenshot, and video tasks, with no bundled code or hidden persistence.

Install this if you want image, screenshot, and video requests to prefer Google media workflows. Be aware it may be selected for many image-related tasks because its trigger is broad, but the inspected artifact does not show hidden code, persistence, or unrelated access.

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
  • 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
Category
Not specified by scanner
Confidence
90% confidence
Finding

The invocation description says to use this skill when the user asks to "create, edit, inspect, compare, or describe images/screenshots, or to generate videos," which is very broad and lacks exclusion conditions or negative examples. This could cause unintended invocation for many ordinary image-related requests where this specific workflow preference may not be appropriate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.