ClawHub
Back to skill

Security audit

Comfy Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a small ComfyUI image-generation skill that discloses sending prompts to a local endpoint and shows no hidden execution, persistence, or exfiltration behavior.

Install only if you intend to use a local ComfyUI instance at 127.0.0.1:8188. Avoid putting secrets or sensitive personal data in image prompts, since the local ComfyUI service may save outputs or keep logs. Non-Chinese readers may need translation because the skill documentation is Chinese-only.

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 (2)

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The visible natural-language instructions and descriptions are entirely in Chinese, which can impose a language constraint on users without opt-in. The policy allows locale constraints only when users are given a choice or the restriction is clearly documented and justified.

Missing User Warnings

Low
Confidence
93% confidence
Finding
The skill explicitly states it sends user prompts to a local ComfyUI HTTP endpoint, but it does not warn users that their input will be transmitted off the agent into another service. Even though the endpoint is localhost, prompts may contain sensitive data and the receiving service may log, persist, or further process that content without the user's awareness.

Static analysis

No suspicious patterns detected.