Security audit
agentgates-voice
Security checks for vulnerabilities and agentic risk
Overview
The skill describes paid AI phone calls with clear consent and spending limits, and contains no hidden executable behavior.
Use only with consenting recipients and an explicit spending limit. Consider what personal information the call instructions, conversation, transcript, and recording may reveal to Agentgates. Review the referenced operator contract before calling. Independent artifact inspection agrees with the scanners' absence of findings; it does not verify the external service's behavior.
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