ClawHub
Back to skill

Security audit

OpenClaw Cost Guard (Budgets + Token-Saving Playbook)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local cost-reporting tool that reads OpenClaw session logs and does not show hidden exfiltration, persistence, or destructive behavior.

Install only if you are comfortable with a local tool reading OpenClaw/Clawdbot session JSONL files to compute usage and cost. Those logs can contain more than billing metadata, although this script only extracts usage-related fields and prints summaries. Review any cron or alert integration yourself and avoid embedding secrets in alert scripts.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs the agent to read session logs from user home directories and optionally use environment variables for pricing, but it does not declare any tool scope such as permissions or allowed-tools. That creates an authorization gap: an agent may access local files and environment-derived data beyond what is explicitly constrained, which is risky even though the stated purpose is legitimate cost monitoring.

Static analysis

No suspicious patterns detected.