ClawHub
Back to skill

Security audit

Smart Cost Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local cost tracker that stores estimated AI spending history on the user's machine and does not include hidden code or external data sharing.

Before installing, be aware that the skill keeps a local spending history file and may activate on broad budget-related wording. Use explicit start/stop tracking commands, and delete ~/.openclaw/cost-log.json if you want to clear the stored history.

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
Confidence
95% confidence
Finding
The trigger list is broad enough to activate on common words like "budget" or generic spending-related phrasing outside a clear cost-tracking intent. This can cause unintended skill activation, which is risky here because the skill may start reading or writing local spending data and influence the agent's response flow when the user did not explicitly request cost tracking.

Static analysis

No suspicious patterns detected.