Security audit
Plugin Intelligence
Security checks for vulnerabilities and agentic risk
Overview
This skill provides disclosed guidance for choosing and validating OpenClaw plugins, without adding code, persistence, credential handling, or hidden execution behavior.
Installers should treat this as a reasoning aid for plugin selection and orchestration. It may lead an agent to evaluate or use other plugins when a task needs external capability, so users should still review the permissions of any plugin selected later.
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.