Security audit
AI Phone Booking (LifeClaw via Finch)
Security checks for vulnerabilities and agentic risk
Overview
The skill provides a clearly scoped phone-booking service with confirmation before calls, approval for paid use, and disclosed retention of personal preferences.
Confirm the recipient and appointment details before each call, verify free-run availability and any charges, and share only necessary personal information. Preferences are retained indefinitely unless you request deletion through support. The clean scanner results are consistent with the inspected instructions; the external connection guide remains unverified.
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
Static analysis
No suspicious patterns detected.