ClawHub
Back to skill

Security audit

Skill Mcp Security Audit

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only MCP security audit checklist, with no bundled executable code, permissions, persistence, or hidden runtime behavior.

Installers should treat this as a security checklist, not an automated scanner. Run the suggested commands only against MCP code you intend to review, and independently verify external incident or CVE claims if they affect a decision.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · README.md (reported line 17)May include surrounding context.

md
What a compromised MCP server can do:
- 🚨 **Exfiltrate data** to external servers (your code, API keys, environment variables)
- 💀 **Execute arbitrary commands** on your machine
- 🔓 **Access files** beyond intended scope (path traversal)
- ⚡ **Chain vulnerabilities** for privilege escalation

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SKILL.md (reported line 18)May include surrounding context.

md
What a compromised MCP server can do:
- 🚨 **Exfiltrate data** to external servers (your code, API keys, environment variables)
- 💀 **Execute arbitrary commands** on your machine
- 🔓 **Access files** beyond intended scope (path traversal)
- ⚡ **Chain vulnerabilities** for privilege escalation