Security audit
skill-graph-audit
Security checks across malware telemetry and agentic risk
Overview
This skill provides documentation for auditing skill reference graphs and does not add hidden execution, persistence, credential access, or destructive behavior.
Install this if you want documentation and workflows for auditing OpenClaw skill references. Review the separate script or plugin it points to before running commands, especially if you point it at private plugin repositories, because the audit necessarily reads skill files under the selected plugins root.
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.
Static analysis
No suspicious patterns detected.