OpenClaw Voice Call Playbook
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only voice-call playbook whose sensitive behavior is disclosed and aligned with outbound calling.
Before installing, confirm the voice-call plugin uses scoped provider credentials, require explicit approval for live calls if unattended calls are not acceptable, use mock mode first, and set retry or rate limits to control cost and accidental outreach.
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.