ClawHub
Back to skill

Security audit

Shuf Tool

Security checks for vulnerabilities and agentic risk

Overview

This is a small line-shuffling skill with a real input-handling bug, but no evidence of hidden execution, persistence, network access, or malicious behavior.

Install only if you are comfortable with a minimal, incomplete shuf helper. Avoid piping untrusted text into it until stdin handling is fixed, because a piped pathname could cause it to print that file's contents instead of shuffling the piped lines.

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
Category
Not specified by scanner
Confidence
98% confidence
Finding

The script's input logic is unsafe for a text-shuffling tool: when no filename argument is given, it reads all of stdin and then passes that content to open() as though it were a filesystem path. This means untrusted piped input can cause the tool to open arbitrary local files instead of shuffling the provided text, leading to unintended file disclosure or confusing behavior that violates the advertised function.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The tool can unexpectedly open a file derived from stdin without any warning, which makes its behavior surprising and unsafe in pipelines or agent workflows. While this is primarily a consequence of the flawed input handling, the lack of user-facing explanation increases the chance of accidental local file reads and data exposure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.