ClawHub
Back to skill

Security audit

Ascii Tool

Security checks for vulnerabilities and agentic risk

Overview

The skill advertises ASCII code conversion, but its bundled script generates ASCII art instead, with no evidence of data theft or persistence.

Review before installing because the package does not appear to do what it advertises. The observed code looks locally contained and low impact, but users expecting ASCII code conversion should require the manifest and implementation to be corrected or clarified.

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 (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared description suggests functionality around ASCII numeric codes, character inspection, or text encoding conversion/analysis. The supplied code does none of that. It defines font glyph mappings and converts input text into multi-line ASCII art for display. There is no logic for examining code points, translating between encodings, or inspecting ASCII values. This is a clear primary-purpose mismatch, though the code does not appear to perform any suspicious undeclared resource access or trigger behavior.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest says the skill converts and inspects ASCII character codes and text encodings, which implies examining numeric codes or encoding representations. This file instead implements a text-to-ASCII-art renderer using predefined font glyphs and prints banner-style output, a materially different behavior.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The inline module documentation explicitly presents this file as an ASCII art generator, while the skill manifest says the skill is for converting and inspecting ASCII character codes and text encodings. This is an active intent mismatch between the documented purpose in code and the declared skill purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.