ClawHub
Back to skill

Security audit

格语

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent image-generation helper for making grid comic story images, with only normal reference-image privacy considerations.

Before installing, understand that reference images or their URLs may be sent to the image-generation tool. Use non-sensitive images and avoid private links, account-protected URLs, or images containing personal information you would not want processed externally.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
89% confidence
Finding

The trigger list contains broad, generic phrases such as '四格漫画', '六宫格', '九宫格', and '故事图', which can cause the skill to activate in conversations where the user did not intend to invoke it. Unintended activation can redirect user flow and cause unnecessary collection or forwarding of user content, including reference image URLs, to downstream tools.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly asks users to provide a character image and later requires passing its URL to imageGenerate, but it does not clearly warn users that their reference image URL will be transmitted to a separate image-generation tool. This creates a privacy and consent risk, especially if the image is personal, sensitive, or hosted at a URL containing identifying or access-related information.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.