Security audit

Ls Tool

Security checks for vulnerabilities and agentic risk

Overview

This is a simple directory-listing skill with no evidence of network access, persistence, destructive actions, or hidden behavior.

Install only if you are comfortable giving the skill visibility into directory names and file sizes for paths the agent can access. Use it on intended project folders rather than sensitive home, credential, or system directories.

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
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: 86% confidence
Finding: The skill exposes file-reading capability through a directory-listing utility but does not declare any explicit tool scope such as permissions or allowed-tools. Even if intended only for listing directories, this omission weakens security boundaries and can allow broader file-system access than reviewers or runtime policy expect, especially when used recursively or on sensitive paths.
Content: No source excerpt is available for this finding.