Back to skill

Security audit

Sort Tool

Security checks for vulnerabilities and agentic risk

Overview

This is a simple local line-sorting skill with no evidence of hidden behavior, network use, persistence, or destructive actions.

This skill appears safe for ordinary text sorting. Before installing, note that it can read whichever file path you ask it to sort and will print that file's contents in sorted form, so avoid using it on sensitive files unless that output is intended.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
83% confidence
Finding

The skill documentation describes reading user-supplied files, but the manifest does not declare any explicit tool scope or permissions boundaries. Even for a simple sorting utility, undeclared file-read capability weakens least-privilege guarantees and can allow the agent runtime or reviewers to miss that the skill may access local files.

Content

No source excerpt is available for this finding.