ClawHub
Back to skill

Security audit

AI图片加水印 | 批量水印 | 版权水印 | 品牌水印 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill gives local ImageMagick or ffmpeg recipes for adding watermarks to images, with behavior that matches its stated purpose.

Install only if you are comfortable with the agent running local image-processing commands and, if ImageMagick is missing, asking to install it through your system package manager. Review batch file patterns before running them so only intended images are modified or copied.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest says the skill 'must trigger' when users ask to add watermarks, and includes broad keywords like '加水印' and 'watermark'. While watermarking is a domain task, the activation guidance does not define exclusions or boundaries, so it could match generic image-editing requests more broadly than intended.

Content

No source excerpt is available for this finding.