ClawHub
Back to skill

Security audit

Spark Context Monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to locally estimate current conversation token usage without hidden transmission, persistence, or account-changing behavior.

Installers should understand that the skill needs access to the current conversation text to estimate token usage, although the reviewed code does not store or upload it. Prefer invoking it with /token if accidental natural-language activation would be disruptive, and verify the package build includes the expected dist/index.js entry.

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 (1)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger phrases are broad, everyday-language prompts such as asking about remaining context or token usage, which can overlap with normal conversation and cause unintended skill activation. In an agent ecosystem, this can redirect user intent, create confusing behavior, and expose session metadata more often than the user explicitly intended.

Static analysis

No suspicious patterns detected.