ClawHub
Back to skill

Security audit

Text Helper

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a simple text-organization training skill with documentation issues but no evidence of harmful behavior.

Before installing, expect a lightweight training/demo skill for text organization. The package may be incomplete or overstate summarization support, so verify that the actual tool implementation exists if you need working keyword or todo-list tools.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Confidence
96% confidence
Finding
The manifest description at L03 says the skill supports "content summary," but the body documentation at L12-L18 enumerates only two tools: extract_keywords and generate_todo_list. The file description at L38 also says src/index.ts implements only keyword extraction and todo list generation, reinforcing that summarization is not part of the implemented behavior described here.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The skill documentation switches into Chinese for the feature descriptions, usage scenarios, and input examples, but does not indicate that this is a region-specific skill or offer an English/localized alternative. This can violate a language or locale policy when users are not given an explicit choice of language.

Static analysis

No suspicious patterns detected.