registry / gimirick-replypilot / 0.3.2

gimirick-replypilot@0.3.2

A TypeScript CLI that automates WhatsApp replies using local or custom OpenAI-compatible LLM providers.

AI Security Review

scanned 18h ago · by lpm-firewall-ai

Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.

Static reason

No blocking static signals were detected.

Trigger

User runs `replypilot start` after setup/login.

Impact

Configured providers receive chat content; the package can autonomously reply from the linked WhatsApp account.

Mechanism

WhatsApp message forwarding to an OpenAI-compatible LLM with automated reply delivery.

Rationale

No install/import-time malicious chain was found, but the package provides an active AI-driven messaging capability that forwards private chat content and sends autonomous replies. Flag as a warning for dangerous dual-use capability.

Evidence

package.jsondist/index.jsdist/cli.jswhatsapp-sessions/./.wwebjs_cache

Network endpoints4

localhost:1234/v1localhost:11434/v1ollama.com/v1localhost:8080/inference

Decision evidence

public snapshot

gimirick-replypilot@0.3.2

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code