NYC

whatsapp-messaging

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The skill instructions require the installation of the @kapso/whatsapp-cloud-api package from the NPM registry. This is a standard external dependency for the skill's core functionality.
  • [COMMAND_EXECUTION] (LOW): The skill utilizes several local Node.js scripts (e.g., list-platform-phone-numbers.mjs, create-template.mjs) to perform administrative and operational tasks. These scripts represent a command execution surface that relies on the integrity of the files within the skill package.
  • [DATA_EXFILTRATION] (LOW): The skill provides capabilities to read private WhatsApp inbox data and message history (client.messages.query()). This involves access to sensitive Personal Identifiable Information (PII) and private communications, creating a data exposure surface if the agent's context is mishandled.
  • [PROMPT_INJECTION] (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8). Because the agent is instructed to read incoming WhatsApp messages, an attacker could send a message containing malicious instructions designed to hijack the agent's logic.
  • Ingestion points: client.messages.query(), GET /{phone_number_id}/messages (SKILL.md).
  • Boundary markers: None identified; the agent processes message bodies directly.
  • Capability inventory: Sending messages, managing templates, and uploading media.
  • Sanitization: No explicit sanitization or filtering of external message content is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:22 PM