ClawHub
Back to skill

Security audit

AI图片压缩 | 批量压缩 | 减小体积 | 优化加载 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward local image-compression skill, with a disclosed optional ImageMagick install and no hidden or unrelated behavior found.

Before installing, confirm you are comfortable allowing the agent to use ImageMagick on selected local image files and to install ImageMagick if it is not already present. Review output files before replacing originals.

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
Confidence
91% confidence
Finding
The skill declares it "must" trigger for broad, common image-size requests, which can cause over-activation and inappropriate routing of user tasks to this skill. In an agent system, mandatory broad triggers increase the chance of hijacking unrelated requests, bypassing better-matched tools, and causing unintended command execution paths such as local package installation or shell-based processing guidance.

Static analysis

No suspicious patterns detected.