Security audit
Apple Messages CLI
Security checks for vulnerabilities and agentic risk
Overview
The skill provides clearly disclosed access to Apple Messages, with limited reads and explicit approval required before sending.
Grant the disclosed macOS permissions only if you want the agent to access private conversations and send messages. Narrow reads by chat, date, and limit, and approve each recipient and message after reviewing a dry-run. All scanner coverage gaps were manually reviewed; macOS runtime behavior and the registry package were not tested.
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