Back to skill

Security audit

WhatsApp Chats

Security checks for vulnerabilities and agentic risk

Overview

This skill does not show exfiltration or persistence, but it reads sensitive local WhatsApp session/contact data and exposes identifiers with limited user-facing disclosure.

Review this before installing if the workspace contains real WhatsApp/Baileys state. It appears read-only and local, but it can reveal private contacts, phone numbers, group identifiers, and the local cache path; use it only where that disclosure is acceptable.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The stated purpose is limited to listing, searching, and analyzing WhatsApp conversations, but the detected behavior extends to local session/credential metadata, contacts, and storage-path disclosure. This mismatch is dangerous because it can mislead users into granting or invoking a skill for harmless conversation browsing when it actually surfaces sensitive local authentication and account-related information.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill exposes code-execution capability via exec(...) but does not declare any tool scope such as permissions or allowed-tools. That makes the privilege boundary unclear and can allow a skill that touches local environment-backed WhatsApp data to run with broader access than users or reviewers expect.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description and usage guidance do not warn that it accesses local WhatsApp data, which is highly sensitive and may include private conversations, contacts, and related account artifacts. In this context, missing disclosure increases the chance of uninformed use and accidental privacy violations because the skill operates against a local Baileys session cache rather than a clearly sandboxed dataset.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description promises listing, searching, and analyzing WhatsApp conversations, but the implementation only inspects local credential/session artifacts and contact metadata. This mismatch is security-relevant because it can mislead users into granting or invoking access to sensitive local WhatsApp state under a broader, inaccurate feature claim, obscuring what data is actually being harvested.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The script reads local WhatsApp session-derived files and contacts.json to enumerate contact IDs, phone numbers, names, and group identifiers, then prints them without any privacy notice, consent flow, or minimization. In this skill context, that is more dangerous because users may expect conversation tooling, not silent extraction of sensitive social-graph metadata from local app state.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The stats output reveals the exact local WhatsApp credential/state directory path, which is unnecessary for normal chat listing or statistics. Exposing internal filesystem paths leaks environment details that can aid follow-on attacks, targeted file access attempts, or user de-anonymization on shared/logged systems.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.