ClawHub
Back to skill

Security audit

Ai Video Generation Skills

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Pixwith media-generation connector that sends prompts and optional reference images to Pixwith as part of its expected function.

Install only if you intend to use Pixwith. Treat prompts and uploaded reference images as data sent to Pixwith, and use a Pixwith API key you are comfortable placing in the MCP configuration.

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
  • 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 (1)

External Transmission

Medium
Category
Data Exfiltration
Content
{
  "mcpServers": {
    "pixwith": {
      "url": "https://api.pixwith.ai/mcp",
      "headers": {
        "Api-Key": "YOUR_PIXWITH_API_KEY"
      }
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.