ClawHub
Back to skill

Security audit

Auto Backup Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a simple backup-skill description whose data-copying behavior is disclosed and purpose-aligned, though users should configure it carefully.

Before installing, choose narrow source directories, avoid backing up secrets unless needed, enable encryption for cloud or shared storage, and confirm restore targets so existing files are not unintentionally overwritten.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill encourages automatic backup and restore of potentially sensitive files to local or cloud destinations, but it does not warn users about privacy, accidental overwrite, retention, restore safety, or the risks of uploading confidential data to third-party storage. In an agent context, silent or poorly explained backup behavior can expose sensitive workspace and memory data or cause unintended data loss during restore operations.

Natural-Language Policy Violations

Low
Confidence
97% confidence
Finding
The natural-language description, usage examples, and metadata are presented in Chinese only. Under the stated policy, forcing a specific language without user opt-in or documented justification is a locale policy violation.

Static analysis

No suspicious patterns detected.