ClawHub
Back to skill

Security audit

Whatsapp Cli

Security checks for vulnerabilities and agentic risk

Overview

This WhatsApp integration discloses its sensitive capabilities and provides meaningful controls over messaging and background collection.

Link only your own account and protect the computer holding its message history and device keys. Review permissions for deletion, group administration and privacy changes; MCP's 'ask' setting does not provide another confirmation prompt. Background collection is optional. The skill warns that this unofficial client may cause account restrictions. Manual inspection addressed the scanner's text-analysis gaps, but the external npm package and engine remain unverified.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The main WhatsApp functionality matches the description. However, the task commands introduce a distinct workflow that changes task records rather than merely accessing or sending messages. Searching local notes also extends the stated search scope beyond WhatsApp messages. These are substantive additional capabilities, not just supporting implementation details.

Content

No source excerpt is available for this finding.

The skill exposes destructive chat operations and account/group administration beyond its declared setup, read, search, and send scope.

Medium
Category
Excessive Agency
Confidence
96% confidence
Finding

The manifest at L004–L005 describes linking WhatsApp and finding, reading, searching, or sending messages. The command guidance at L042–L047 additionally exposes chat deletion/clearing, group membership and administrator changes, contact blocking, and account privacy changes; these are separate account-management capabilities, not necessary implementation details of the stated messaging workflows.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 313)May include surrounding context.

md
An agent that cannot run commands (a chat app such as Claude Desktop, a remote agent) uses the MCP server instead:
`wa personal mcp serve`. The profile's `permissions` decide which commands it offers, the same as on the command line,
through `wa_tools_search`, `wa_read` and `wa_write`; there is no confirmation form. When you can run commands, use
the commands above instead of MCP. `wa personal mcp config` prints the entry with full paths.
`wa personal mcp serve --http --public-url https://laptop.example.ts.net` (the owner's own tunnel address) serves behind
the owner's tunnel with its own login.

Static analysis

No suspicious patterns detected.