ClawHub
Back to skill

Security audit

Comfyui 7e6098

Security checks for vulnerabilities and agentic risk

Overview

This is a simple ComfyUI tutorial guide skill with broad activation wording but no executable behavior, persistence, credential access, or destructive instructions.

Install only if you want a lightweight ComfyUI learning/reference skill. Be aware it may trigger for broad ComfyUI-related requests, so users may want tighter trigger wording for cleaner routing.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest trigger field contains promotional and descriptive phrases rather than precise invocation commands, such as long tutorial slogans. These vague triggers can create unreliable matching behavior and overbroad activation, allowing the skill to be selected for loosely related user input.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger section includes broad activation conditions such as users saying generic terms like "comfyui" or needing "comfyui-related help." This can cause the skill to activate in situations far beyond the author’s intended scope, increasing the chance of inappropriate routing, prompt interference, or accidental invocation over more suitable skills.

Content

No source excerpt is available for this finding.