ClawHub
Back to skill

Security audit

Vvvv Shaders

Security checks for vulnerabilities and agentic risk

Overview

This skill is a domain-specific shader reference and does not request risky access or perform hidden actions.

Install this if you want shader-specific help for vvvv gamma or Stride. Be aware it may activate for general shader or compute discussions when vvvv context is present, but the content inspected is documentation-oriented and low risk.

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
Confidence
94% confidence
Finding
The trigger guidance is unusually broad because it says to activate even on generic terms like 'HLSL', 'shader', 'GPU effect', 'render pass', or 'compute' in a vvvv context. In an agent system, this can cause unnecessary or incorrect skill routing, which may increase the chance of irrelevant instructions being applied or the model overfitting to this skill when a narrower coding or graphics skill would be more appropriate.

Static analysis

No suspicious patterns detected.