whatsapp-macos
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes native macOS commands such as
/usr/bin/opento launch the WhatsApp application and uses accessibility APIs to simulate user interactions like clicking and typing. - [DATA_EXFLLTRATION]: The skill has the capability to read WhatsApp messages and contact lists. While this is the primary purpose of the skill, it represents a potential data exposure surface if the agent were to exfiltrate this information to an external service. However, no evidence of unauthorized network transmission was found in the provided code.
- [SAFE]: The skill includes robust internal safety guidelines, such as mandatory user confirmation before sending messages and verification of the active chat recipient to prevent misdirected messages.
- [SAFE]: External dependencies are sourced from trusted or well-known repositories, including official Apple libraries and the Model Context Protocol SDK.
Audit Metadata