Security audit
clawvet-guard
Security checks for vulnerabilities and agentic risk
Overview
This skill is a straightforward security-check wrapper for scanning OpenClaw skills before use, with the main consideration being trust in the external ClawVet CLI it runs.
Install only if you are comfortable letting it run the ClawVet npm CLI against skill files. Use the automatic install action only for workflows where you explicitly asked to install or enable a skill; for safety-only checks, treat the result as advice rather than consent to install.
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.