ClawHub
Back to skill

Security audit

AI图片压缩 | 批量压缩 | 减小体积 | 优化加载 | LinkPix

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward image-compression skill that uses normal local tools and does not show hidden, persistent, or unrelated behavior.

Before installing, be aware that the skill may ask the agent to install ImageMagick if it is not already available, and it will create compressed image outputs locally. Review output paths before running batch commands so original files are not accidentally 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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill metadata explicitly says image compression requests 'must trigger' and includes broad keywords like reducing image size or upload-size limits, which are common requests that may overlap with other tools or user intents. This can cause over-invocation of the skill without clear guardrails, reducing user control and potentially routing unrelated image tasks through this skill inappropriately.

Static analysis

No suspicious patterns detected.