ClawHub
Back to skill

Security audit

move-day-orchestrator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local household-moving planner that stores only its own move inventory state and does not show network, credential, hidden execution, or persistence behavior.

Install only if you want a local moving-planning CLI. It will create or update a JSON state file for your move plan; avoid pointing --state at unrelated important files.

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
94% confidence
Finding

The skill describes and demonstrates a local script that reads and writes state (move_state.json) but does not declare any explicit tool scope such as file permissions or allowed tools. That mismatch weakens least-privilege guarantees: an agent or runtime may grant broader filesystem capabilities than users expect, increasing the chance of unintended file access or modification. In this context the script is framed as local-only and benign, which lowers the likelihood of abuse, but the absence of explicit scope is still a real security control gap.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.