Back to skill

Security audit

Ln Tool

Security checks for vulnerabilities and agentic risk

Overview

This is a small local link-creation skill with no evidence of hidden persistence, credential access, network activity, or exfiltration, though its documentation overstates what the bundled script does.

Install only if you are comfortable with a skill that can create local filesystem links. Review paths before use, avoid force replacement in sensitive directories, and note that the bundled script currently supports only symbolic links despite the broader documentation.

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
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 declared description says the skill creates both hard and symbolic links, but the provided code only creates symbolic links via os.symlink and has no logic for hard link creation (such as os.link). Its primary purpose is still link creation, so the mismatch is limited but material because part of the declared functionality is not actually present.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Documenting force-replacement behavior without an explicit warning normalizes a destructive operation that can remove an existing destination path. In a file-manipulation skill, this increases the chance that an agent or user overwrites important files or links unintentionally, especially when operating on attacker-influenced paths or in sensitive directories.

Content

No source excerpt is available for this finding.