ClawHub
Back to skill

Security audit

TinkerClaw Token Efficiency Guide

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill that gives manual token-saving guidance, with disclosed optional cron and file-moving examples but no executable install behavior.

Before using the guide, review any manual crontab entries or AGENTS.md/openclaw.json edits because they can change scheduling, model choice, and answer quality. The artifact itself does not execute code or access credentials.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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 (3)

Session Persistence

Medium
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · GUIDE.md (reported line 83)May include surrounding context.

md
Read it. That is the whole interface. The code blocks inside it are meant to be
copied by the operator into `openclaw.json`, into `AGENTS.md`, or into
`crontab -e`; nothing in this directory does that on its own.

Two details worth knowing before quoting the file:

Session Persistence

Medium
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · GUIDE.md (reported line 267)May include surrounding context.

md
Read it. That is the whole interface. The code blocks inside it are meant to be
copied by the operator into `openclaw.json`, into `AGENTS.md`, or into
`crontab -e`; nothing in this directory does that on its own.

Two details worth knowing before quoting the file:

Session Persistence

Medium
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

md
Read it. That is the whole interface. The code blocks inside it are meant to be
copied by the operator into `openclaw.json`, into `AGENTS.md`, or into
`crontab -e`; nothing in this directory does that on its own.

Two details worth knowing before quoting the file:

Static analysis

No suspicious patterns detected.