ClawHub
Back to skill

Security audit

Context Window Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused context-usage reporter that reads local OpenClaw session metadata and transcripts to show token usage, with no evidence of exfiltration or hidden behavior.

Install this only if you are comfortable with a local helper reading OpenClaw session metadata and transcript files to calculate token usage. The auto-check feature should remain off unless you explicitly want a persistent local message counter for periodic reports.

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 (1)

Vague Triggers

Low
Confidence
90% confidence
Finding
The phrase "Any question about context usage" is an open-ended activation condition in a markdown skill description. Although surrounding examples are more specific, this line broadens the trigger scope without clear boundaries or negative examples for near-matches, increasing the chance of unintended invocation.

Static analysis

Detected: suspicious.prompt_injection_instructions

Prompt-injection style instruction pattern detected.

Warn
Code
suspicious.prompt_injection_instructions
Location
SKILL.md:73