ClawHub
Back to skill

Security audit

ComfyUI Video

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent ComfyUI video-generation helper; its SSH and browser-script behavior is disclosed and aligned with managing a remote GPU workflow.

Before installing, confirm you are comfortable with a skill that may guide your agent to run SSH commands and browser-console JavaScript for ComfyUI. Use it only with authorized ComfyUI hosts, review commands before execution, and close any background SSH tunnel when finished.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill includes explicit network-capable operational instructions such as SSH tunneling and remote host commands, but it does not declare any tool scope or allowed-tools restrictions. This creates a capability/permission mismatch where an agent may be induced to perform remote network actions without clear authorization boundaries, increasing the risk of unintended data access or command execution on external systems.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The user-facing doc comment and inline guidance are written entirely in Chinese, which imposes a specific language on users of the skill. There is no indication of language choice, opt-in, or a documented region-specific reason for this constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.