ClawHub
Back to skill

Security audit

OpenClaw wacli Playbook

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent WhatsApp CLI wrapper, but it grants access to sending messages and syncing or searching private WhatsApp history without enough privacy and persistence guardrails.

Review this before installing if WhatsApp contains sensitive personal, business, or third-party messages. Use it only when you intentionally want the agent to access WhatsApp, confirm all outbound messages, avoid broad sync/backfill unless necessary, and consider using a scoped store path or deleting ~/.wacli data when finished.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly enables WhatsApp history sync, search, and backfill of chats, which can expose sensitive personal or third-party communications if invoked without strong privacy guardrails. While the skill includes some safety around message sending, it does not require consent checks, data-minimization guidance, or warnings before accessing message history, making privacy misuse more likely.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.