Back to skill

Security audit

Julia's OpenClaw Token Optimizer

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent cost-optimization helper, but it tells the agent to patch gateway model-selection configuration without clear user approval, scoping, or rollback guidance.

Install only if you are comfortable with an agent changing OpenClaw model-selection settings. Before using it, require a dry-run recommendation, review the exact config patch, confirm who is authorized to apply it, and keep a rollback copy of the prior modelSelection settings.

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
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
93% confidence
Finding

The skill description is overly broad and action-oriented ('scans', 'benchmarks', 'patches config') without clear invocation boundaries, approval requirements, or exclusions. That ambiguity can cause the agent to apply the skill in contexts where configuration changes or external lookups were not explicitly intended, increasing the chance of unsafe or unauthorized behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly instructs patching gateway configuration to change model selection, but it provides no warning, confirmation step, rollback guidance, or authorization check before modifying system configuration. This is dangerous because an agent could silently alter runtime behavior, cost controls, availability, or quality characteristics across sessions or users, leading to operational disruption or policy violations.

Content

No source excerpt is available for this finding.