Security audit
Call My Agent
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed setup guide for a local OpenClaw voice line, with sensitive install, credential, remote access, and persistence steps gated by user confirmation.
Before installing, confirm each step that changes your machine: package install, npm install, Tailscale Serve, and any background service. Use the default 127.0.0.1 binding unless you intentionally want broader exposure, and keep OpenAI keys inside OpenClaw auth rather than pasting them into chat.
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
60/60 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.