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 watermarks to images and does not show hidden, destructive, or unrelated behavior.

Before installing, confirm you are comfortable with a skill that may run local ImageMagick or ffmpeg commands and may require installing ImageMagick. Review output paths first, especially for batch runs, so originals are not unintentionally overwritten.

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
95% confidence
Finding

The trigger conditions and keyword list are broad enough to overlap with common user phrasing, and the description says the skill 'must trigger' for those requests. This can cause unintended invocation of the watermarking skill in contexts where the user may be discussing watermarking generally, comparing tools, or asking for a different action, leading to incorrect routing or unexpected file-processing behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

文件中的自然语言说明全部为中文，且未说明是否可根据用户偏好切换语言或接受其他语言输入。若组织要求不应在未获用户同意的情况下强制特定语言，这种单一语言约束可能构成语言/区域策略问题。

Content

No source excerpt is available for this finding.