ClawHub
Back to skill

Security audit

Token Usage

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to use disclosed, purpose-aligned usage logging rather than hidden or unrelated data collection.

Before installing, check where the skill stores its usage history, whether telemetry can be disabled, and how to delete or rotate old records. Avoid using it in sensitive workspaces unless you are comfortable retaining metadata about agent runs, models, timestamps, and token usage.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill explicitly mandates appending a structured usage record to a persistent NDJSON file on every run, even when the user did not request storage. This creates silent retention of per-agent operational metadata and spending history, which can expose behavioral patterns and accumulate sensitive workspace telemetry over time.

Ssd 3

Medium
Confidence
98% confidence
Finding
This section requires persistent recording of per-agent usage history without explicit user consent, including agent identifiers, categories, token counts, models, and timestamps. Even without credentials, this is a privacy and data-governance issue because the skill turns a reporting action into durable telemetry collection.

Static analysis

No suspicious patterns detected.