ClawHub
Back to skill

Security audit

Test Tool

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small file-test helper with an overbroad description but no evidence of hidden access, persistence, data theft, or destructive behavior.

Installers should understand that this appears safe but incomplete: it only handles basic filesystem tests despite documenting broader shell-test behavior, so users relying on numeric or string comparisons may get incorrect failures until the description or implementation is corrected.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The declared description says the skill evaluates conditional expressions for file testing, string comparison, and arithmetic checks. The provided code only supports filesystem tests for path existence, regular files, and directories via command-line arguments, and exits with status 0/1 accordingly. There is no implementation of string comparison or arithmetic evaluation. While the file-test portion aligns, the overall declared purpose materially overstates the capability set, so this is a description-behavior mismatch.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

Examples

bash
test-tool -f /etc/passwd
test-tool -d /home/user
test-tool 5 -gt 3

Static analysis

No suspicious patterns detected.