Security audit

OpenClaw Token Optimizer

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent OpenClaw cost-optimization guide, but it recommends persistent memory writes and broad local memory indexing without enough user-control and privacy guidance.

Before installing, review any suggested OpenClaw config changes carefully. Only enable memoryFlush, memorySearch, qmd indexing, heartbeat, or subagents for paths and workloads you understand, and avoid persisting secrets, credentials, private logs, or broad workspaces unless you have a clear retention and deletion plan.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The manifest description says to use the skill when a user asks to "reduce OpenClaw token spend, speed up sessions, shrink context, or configure openclaw.json and memory search settings." Several of these conditions are broad outcome-oriented phrases rather than specific invocation boundaries, and the file provides no negative examples or exclusion conditions to clarify when this skill should not activate.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The file recommends automatic memory persistence and indexing behaviors, including writing lasting notes to memory files and enabling searchable memory backends, but it does not warn that sensitive user or workspace data may be stored durably and later retrieved. In a token-optimization skill, this is more dangerous because the guidance frames memory writes as an efficiency feature, which can encourage broad persistence of data without consent, retention limits, or secrecy controls.

Static analysis

No suspicious patterns detected.