Back to skill

Security audit

OpenClaw Cost Guardian

Security checks for vulnerabilities and agentic risk

Overview

This cost-monitoring skill is purpose-aligned, but it describes automatic monitoring of every conversation and daily reporting without clear opt-in, destination, retention, or disable controls.

Review this skill carefully before installing. It may be useful for cost tracking, but only enable it if you are comfortable with conversation-level usage monitoring and daily reports; look for clear controls to opt in, disable monitoring, and understand what usage data is stored or shared.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad, generic requests like '帮我省钱' and '优化配置' that are likely to appear in normal conversation, causing the skill to activate unexpectedly. In a skill that claims to automatically monitor usage and send reports, accidental activation increases the risk of unintended monitoring behavior, confusing model-switch recommendations, and surprise automated actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill states that it will automatically monitor every conversation, automatically recommend models, trigger cost warnings, and send daily cost reports, but it does not clearly warn users about this ongoing collection and reporting of usage data. This is dangerous because users may not realize that their activity patterns, token consumption, and potentially task metadata are being continuously observed or surfaced through reports without explicit opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
71% confidence
Finding

Nearly all user-facing instructions, examples, and trigger phrases are presented only in Chinese, and the document does not indicate that the skill is region-specific or that users may choose another language. This can amount to an implicit language policy constraint without opt-in or justification.

Content

No source excerpt is available for this finding.