ClawHub
Back to skill

Security audit

migu-attraction-query

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed travel lookup helper that only queries a specific public Migu attraction API for scenic spots, hotels, and food results.

Install only if you are comfortable with the agent making unauthenticated POST requests to the documented Migu travel API when you ask for Chinese city attraction, hotel, or food information. Results come from the remote service, so verify important travel details independently.

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
95% confidence
Finding

The skill documentation describes direct network access to external endpoints and even provides executable commands, but it declares no explicit tool scope or permissions. This creates a least-privilege and governance gap: an agent/runtime may permit broader network use than intended, making outbound access harder to audit, constrain, or review.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.