ClawHub
Back to skill

Security audit

Backup 3-2-1 Auditor

Security checks for vulnerabilities and agentic risk

Overview

This skill is an offline backup-audit helper that stores user-entered backup inventory locally and does not show hidden network, credential, destructive, or persistence behavior.

Installers should understand that backup asset names, locations, value classes, and restore-test notes will be saved locally in backup-registry.json next to the skill. Use generic labels if the inventory itself is sensitive, and protect or delete that registry as appropriate.

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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This code persists user-supplied backup inventory data to backup-registry.json, and the same persistence behavior is used by commands that update assets and drill logs. Although the module docstring mentions a local JSON registry, there is no user-facing warning at the write points about storing potentially sensitive asset names, backup locations, or restore-test results on disk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.