ClawHub
Back to skill

Security audit

AI图片加水印 | 批量水印 | 版权水印 | 品牌水印 | LinkPix

Security checks for vulnerabilities and agentic risk

Overview

This skill gives straightforward local instructions for adding visible watermarks to images, with no hidden code, credential use, persistence, or data exfiltration behavior found.

Before installing, be aware that the skill may ask the agent to install ImageMagick and run local commands over image files. Confirm the input folder, output folder, watermark asset or text, and review one sample before approving a batch run.

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
Confidence
90% confidence
Finding
The trigger metadata includes broad terms such as '图片加水印' and '加水印', plus language stating the skill 'must trigger' when users request watermarking. This can cause over-activation on generic image-editing requests and route conversations into shell-command-based workflows without sufficiently checking user intent or whether another skill is more appropriate.

Vague Triggers

Low
Confidence
82% confidence
Finding
The activation guidance gives examples of when to trigger but does not define clear boundaries for when not to trigger. In an agentic environment, ambiguous trigger rules can cause the skill to activate on loosely related requests, increasing the chance of incorrect tool selection and unintended file-processing actions.

Static analysis

No suspicious patterns detected.