Security audit
Openclaw Prompt Shield
Security checks across malware telemetry and agentic risk
Overview
This is a local prompt-injection scanning skill whose file access and pattern lists match its stated defensive purpose.
Install this only if you want a local first-pass input filter. It can read input files and write reports or sanitized files at paths you provide, so choose those paths deliberately and do not treat its pattern-based verdicts as a complete security boundary.
SkillSpector
By NVIDIA
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
VirusTotal
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.