ClawHub
Back to skill

Security audit

language-polisher

Security checks for vulnerabilities and agentic risk

Overview

This is a simple text-polishing skill with no code execution, persistence, credential use, or hidden data access.

Install this if you want a lightweight wording and grammar polishing helper. Be aware it may trigger for general rewrite or polish requests, so review the output when exact wording matters.

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
92% confidence
Finding

The manifest description says the skill should be used for broad requests like 'improving wording' and includes generic keywords such as 'polish' and 'rewrite sentence'. These phrases are common everyday instructions and the file does not provide exclusion conditions or clearer scope boundaries to prevent unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.