ClawHub
Back to skill

Security audit

Cut Tool

Security checks for vulnerabilities and agentic risk

Overview

This skill claims to extract delimited fields, but its shipped script only outputs the first five characters of each input line.

Review carefully before installing. The package does not show signs of credential theft, persistence, or destructive behavior, but it is materially misleading as a data-processing tool and may silently truncate data instead of extracting requested fields.

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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill metadata and documentation claim delimiter-based field extraction similar to cut, but the analyzed behavior indicates it instead performs fixed-width character truncation and does not actually parse delimiters or extract columns. This can mislead downstream agents into using the tool for CSV/TSV processing and produce silently incorrect outputs, which is dangerous in automation pipelines that make decisions based on parsed fields.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The implementation does not perform delimiter-based field or column extraction as advertised; it simply truncates every input line to the first 5 characters. This mismatch can silently corrupt data processing pipelines, causing downstream tools or users to trust incorrect output and potentially omit important fields from security-relevant or business-critical data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.