Back to skill

Security audit

WAHA Onboarding

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for WAHA WhatsApp onboarding, but it links a WhatsApp account and exposes a phone number in session metadata without enough scope, privacy, or revocation guidance.

Review this skill before installing if you are comfortable linking WhatsApp through WAHA. Only use it with a WAHA deployment you trust, and remove the linked device in WhatsApp when access is no longer needed. Prefer a version that avoids phone numbers in session names and includes explicit consent, scope, retention, and revocation instructions.

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
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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly asks for and sanitizes a user's phone number, then uses it as a session identifier, but provides no privacy notice, retention guidance, or warning about how this personal data will be processed. Phone numbers are sensitive identifiers, and embedding them directly into session names increases exposure through logs, command history, and operational metadata.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill requests a WhatsApp pairing code and instructs the user to link their account, but does not clearly warn that this action authorizes a session with access to the user's WhatsApp data and actions. Without explicit consent and scope disclosure, a user may unknowingly grant broad account access, which could lead to message exposure, impersonation, or unauthorized account operations if the session is misused.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.