Security audit
OpenClaw: trust validation
Security checks across malware telemetry and agentic risk
Overview
This is a simple prompt-based skill that tells OpenClaw to verify old memory against local files before relying on it.
Review the exact prompt text before adding it to OpenClaw config, especially because it changes persistent agent behavior. Expect it to perform local file and text searches only for paths or symbols referenced by memory before relying on that memory.
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
64/64 vendors flagged this skill as clean.