ClawHub
Back to skill

Security audit

What has this cost so far? Tokens and cost

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local cost-reporting helper that reads OpenClaw transcripts and prints aggregate token and cost totals.

Install this only if you are comfortable with the agent reading your local OpenClaw session transcripts to compute token and cost totals. The inspected script does not send data elsewhere or modify files, but transcript contents may still be sensitive.

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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
83% confidence
Finding

The skill instructs the agent to run local commands and a Node script against transcript data, but it does not declare any explicit tool scope or permissions boundary. That mismatch can cause the runtime or reviewer to underestimate the skill's access needs, and because transcripts may contain sensitive usage and conversation data, undeclared environment or local execution capabilities increase the risk of unintended data exposure or overbroad execution.

Content

No source excerpt is available for this finding.