whatsapp-by-online-live-support
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the
@membranehq/clipackage from the npm registry. This is a standard dependency used to facilitate communication with the Membrane platform. - [COMMAND_EXECUTION]: The instructions involve executing shell commands using the
membraneCLI to manage connections, perform authentication, and run actions. These commands are integral to the skill's primary function of integrating with the WhatsApp Business API. - [INDIRECT_PROMPT_INJECTION]: The skill acts as a bridge for WhatsApp message data and records, representing a potential ingestion surface for untrusted external content.
- Ingestion points: External data is retrieved through
membrane action runandmembrane requestcommands. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands in the retrieved data.
- Capability inventory: The skill possesses capabilities for network operations and connection management via the CLI.
- Sanitization: No explicit sanitization or validation logic is provided for the incoming WhatsApp data.
Audit Metadata