ClawHub
Back to skill

Security audit

Word Counter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local word-count and text-analysis helper with disclosed, user-directed file reading.

This appears safe for normal use. Only point it at files you actually want analyzed, since the --file option will read the chosen file and print derived statistics and keywords locally.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding
The skill documentation advertises command-line usage with a `--file` option and references a script that can read local files, but the skill declares no `permissions` or `allowed-tools` scope. That mismatch can lead to undeclared file access capability being exposed without explicit review or least-privilege controls, increasing the chance of unintended sensitive file reads when the skill is invoked on attacker-influenced paths.

Static analysis

No suspicious patterns detected.