ClawHub

PAPI - WhatsApp API

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only WhatsApp automation skill with powerful but clearly advertised messaging, group, catalog, and integration features.

Install only if you intend to let an agent assist with a PAPI/WhatsApp automation account. Keep the API key private, approve sends and group/catalog changes deliberately, and configure webhooks or WebSockets only for trusted HTTPS/WSS destinations allowed to receive WhatsApp event data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill documents powerful state-changing operations such as deleting instances, creating groups, managing participants, sending messages, and configuring webhooks without any warning, confirmation guidance, permission model notes, or cautions about misuse. In an agent context, this increases the likelihood that an LLM or user will invoke destructive or privacy-affecting actions unintentionally, leading to spam, unauthorized group changes, service disruption, or data exfiltration via webhooks.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The webhook and WebSocket integration docs encourage forwarding message events to external endpoints but do not mention security controls such as TLS validation, endpoint trust, payload minimization, authentication, signature verification, or privacy implications. In a messaging platform handling WhatsApp events, this omission can lead operators to expose sensitive message metadata or content to third-party servers without adequate safeguards, increasing the risk of data leakage or interception.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal