ClawHub
Back to skill

Security audit

Table Tool

Security checks for vulnerabilities and agentic risk

Overview

This is a small local table-formatting skill with no network, persistence, or hidden execution behavior; its file-reading behavior is expected for formatting user-provided data files.

Installers should treat this as a local formatting helper. Review which files are passed to it, because any file path supplied for formatting may be read and its contents printed as a table.

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
  • 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
Findings (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The tool's stated purpose is table formatting, but when --csv is provided a non-inline value, it opens and reads an arbitrary local file path. In an agent setting, this creates unintended file-read capability that can expose sensitive local data if user-controlled input is passed through to the skill.

Content

No source excerpt is available for this finding.