Security audit
OptimoClaw
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed OpenClaw token-cost advisor that reads relevant OpenClaw configuration and usage data and only recommends user-reviewed changes.
Before installing, be aware that the skill will ask an agent to read OpenClaw configuration and usage data, which can reveal operational details such as profile names, models, gateway connection details, and session usage. It should not expose API keys according to the artifact, and it does not apply configuration changes automatically; review any suggested openclaw config set command before running it.
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
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Static analysis
No suspicious patterns detected.