ClawHub
Back to skill

Security audit

Mcp Tool Integrator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-style MCP integration guide with disclosed credential, install, and write-operation risks, and it repeatedly advises least privilege, read-only access, confirmation, and audit logging.

Before installing, verify the referenced MCP packages and current MCP documentation, fix the malformed frontmatter if the marketplace requires valid metadata, and only configure integrations with least-privilege credentials, read-only defaults, explicit confirmation for write actions, and audit logging.

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 (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 569)May include surrounding context.

md
**⚠️ Security note:** Always use read-only connections. Never expose write permissions without approval workflows.

写入类操作必须走审批流程，并保留完整的调用审计记录。

Static analysis

No suspicious patterns detected.