ClawHub
Back to skill

Security audit

Token Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill only instructs the agent to show current conversation token and cost metrics, with no code, persistence, or hidden behavior found.

Installers should expect this skill to surface token and cost information for the current conversation, sometimes proactively after long or complex work. Users who only want usage reports on direct request may want the trigger wording narrowed, but the artifact does not show malicious or high-impact behavior.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill’s trigger list includes very broad generic terms such as "cost" and "usage," which can appear in many unrelated conversations. This can cause the skill to activate outside the user’s clear intent, leading to unsolicited access to session metrics and potentially exposing conversation usage or spending information unexpectedly.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The instruction to trigger when a "long conversation ends" or to "proactively report" after complex tasks is ambiguous and permits unsolicited invocation without a direct user request. In practice, this can create privacy and UX issues by surfacing billing or session statistics when the user did not ask for them.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.