Security audit
AgentSafe Scan
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed hosted static scanner for OpenClaw skill installs, with no hidden execution or local persistence found.
Install only if you are comfortable sending skill URLs or skill markdown to the AgentSafe hosted service. Keep payloads limited to skill text, do not include secrets or private personal data, and remember its results are heuristic guidance rather than a formal audit or safety guarantee.
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.