Security audit
OpenClaw Voice Call Playbook
Security checks for vulnerabilities and agentic risk
Overview
This skill is a narrow guide for making user-approved outbound voice calls through an existing OpenClaw plugin, with clear boundaries and no bundled executable code.
Before installing, make sure the voice-call plugin is configured only with intended provider credentials and caller numbers, test flows in mock mode, and require explicit approval for each destination and retry policy because live calls can incur cost and reach real people.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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