whapi

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The required workflow involves configuring webhooks to receive incoming WhatsApp messages sent by outsiders, which exposes the agent to outsider-authored free text via webhook HTTP POST payloads.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). An operational dependency on the whapi-mcp npm package is fetched via npx during setup and runtime instructions, which runs external remote code as a core part of the skill's execution mechanism.