ClawHub
Back to skill

Security audit

mcp-developer

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown MCP development helper with no bundled code, install hooks, persistence, or hidden data handling.

Install this skill if you want an agent to help with MCP server or client development. Because it discusses integrations with filesystems, APIs, databases, authentication, and deployment, review any concrete implementation changes the agent proposes before granting credentials or production access.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill defines broad expertise and behavior but does not clearly constrain when it should be invoked or what tasks are out of scope. In an agentic system, ambiguous activation can cause the skill to be selected for loosely related requests, increasing the chance it handles sensitive integration, tooling, or security decisions without appropriate specialization boundaries or user intent checks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.