ClawHub
Back to skill

Security audit

Wc Lines Tool

Security checks for vulnerabilities and agentic risk

Overview

This skill appears safe to install, but its documentation promises more line-counting features than the bundled script actually provides.

Expect this to work only as a simple stdin line counter unless the package is updated. Do not rely on the advertised file, JSON, threshold, blank-line, code-line, or comment-line features without testing them first.

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 (1)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared description promises a multi-metric line analysis tool that distinguishes total, blank, code, and comment lines in text files. The actual code only reads from standard input and outputs a single number: the total line count. This is a materially narrower behavior than described, so the description does not accurately represent the implementation.

Content

No source excerpt is available for this finding.