ClawHub
Back to skill

Security audit

Restore

Security checks for vulnerabilities and agentic risk

Overview

This is a simple backup and restore planning workflow with no code, hidden access, or persistence.

This skill is reasonable to install if you want structured help with backup and disaster recovery planning. Be aware it may be offered for adjacent backup or reliability discussions, but it should ask before applying the workflow.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger section says to offer the workflow when a user mentions "backup", "restore", "DR", or closely related work, which is broad and leaves the boundary of activation unclear. The phrase "closely related work" especially lacks specificity and could cause the skill to be invoked in conversations that only tangentially touch these topics.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.