OpenClaw Token Usage

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:22 PM UTC
• Version:
  1.2.0

Overview

This is a local reporting skill that summarizes OpenClaw token usage from local transcripts and does not show hidden networking, credential use, or destructive behavior.

Install only if you are comfortable letting the skill read local OpenClaw transcript metadata for the time range you request. Use narrow date ranges and filters when possible, and treat exported JSON, CSV, or Markdown reports as potentially sensitive because they may reveal usage patterns, model names, agent names, and session identifiers.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 90% confidence
• Finding: The skill instructs the agent to read local transcript files under ~/.openclaw/agents/*/sessions/ and optionally write JSON, CSV, or Markdown outputs, but it does not declare any corresponding permissions. This creates a trust and consent gap: a user or platform may believe the skill is low-risk while it can access potentially sensitive local usage history and persist derived data to disk.

VirusTotal

64/64 vendors flagged this skill as clean.