ClawHub
Back to skill

Security audit

backup-manager

Security checks for vulnerabilities and agentic risk

Overview

This backup skill is coherent and purpose-aligned, but users should confirm backup scope, destination, secret handling, and retention before letting it rotate old backups.

Before installing, decide where backups should go, what should be excluded, whether secrets may be included, and how many backups to retain. Require a preview before the first rotation or any deletion of old backups.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly says to "act, don't ask" when a user mentions backup-related requests, which can cause the agent to initiate file operations without clearly confirming scope, target paths, exclusions, or destination. In a skill with read/write/exec permissions, broad invocation language increases the risk of unintended backups, accidental inclusion of sensitive files, or disruptive actions in the wrong project context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill authorizes rotation by deleting older backups, but the user-facing guidance does not elevate this as a destructive action requiring explicit confirmation or a safe retention policy check. If triggered automatically or in the wrong directory context, this could permanently remove recovery points and reduce resilience precisely when backups are needed most.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.