Security audit
Agent Rule Audit
Security checks across malware telemetry and agentic risk
Overview
This markdown-only skill gives scoped guidance for auditing OpenClaw agent behavior files and does not include executable code, persistence, network activity, or hidden authority.
Install this only in workspaces where you are comfortable having private agent rules, memory, identity, or user-profile files analyzed. Review audit results before sharing them, because they may summarize sensitive behavior-layer content.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.