ClawHub
Back to skill

Security audit

database-optimizer

Security checks for vulnerabilities and agentic risk

Overview

The skill is a database tuning helper, but it encourages direct database changes without clearly requiring user approval, backups, or production safeguards.

Review this skill before installing if it may be used against production or business-critical databases. Use it for diagnosis and recommendations by default, and require explicit approval, verified backups or snapshots, a rollback plan, staging validation, and a maintenance window before allowing it to change indexes, schemas, configuration, replication, or query behavior.

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly instructs the agent to 'implement comprehensive performance improvements' without requiring safeguards such as staging validation, backups, change approval, rollback plans, or confirmation that the target is non-production. In a database-optimization context, these actions can directly alter indexes, schemas, configuration, or query behavior on live systems, risking outages, degraded performance, or unintended effects on data availability and integrity.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.