ClawHub
Back to skill

Security audit

Umeå Lunch

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public lunch menu data from a disclosed restaurant guide site and does not show hidden, destructive, persistent, or credential-related behavior.

Install this if you are comfortable with the agent making a live request to umealunchguide.se when you ask about Umeå lunch options. There is no evidence of credential access, local file indexing, persistence, or unrelated system changes in the inspected artifact.

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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill invokes a Python script that fetches live data from an external site, which implies network access, but the skill metadata does not declare any explicit tool scope such as permissions or allowed-tools. This creates a policy and containment gap: an agent may execute network-capable code without an auditable, least-privilege declaration, increasing the risk of unexpected outbound requests or future capability creep.

Static analysis

No suspicious patterns detected.