wacli

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the 'wacli' CLI tool to perform WhatsApp operations such as authentication, chat listing, and message searching.
  • [EXTERNAL_DOWNLOADS]: The skill's metadata specifies the installation of the 'wacli' binary from a public GitHub repository using Homebrew or Go.
  • [DATA_EXFILTRATION]: The skill includes a command to send files from the local filesystem to WhatsApp contacts. While this is a primary feature of the tool, it constitutes a potential path for data exposure if misused.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from WhatsApp message history which could contain malicious instructions. Ingestion points: Tool output from 'wacli messages search' and 'wacli chats list'. Boundary markers: None explicitly defined. Capability inventory: Network access and file system access via the 'wacli' binary. Sanitization: The skill relies on agent instructions to confirm actions with the user before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 10:45 PM
Security Audit — agent-trust-hub — wacli