Security audit

Mcp Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward MCP server scaffolder, with file and configuration generation that matches its stated purpose.

Before installing or using it in an existing repository, review the generated project files, dependencies, and any MCP client configuration before applying them, especially if the generated server will access internal APIs or credentials.

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

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill explicitly scaffolds MCP servers, generates files, and provides editor/runtime configuration, but it does not warn that using the skill may create or modify project files and local MCP configuration. This can lead users to approve workspace changes without understanding the scope, increasing the risk of unintended code, config, or integration changes in sensitive repositories.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.