Back to skill

Security audit

Chat API for WhatsApp

Security checks for vulnerabilities and agentic risk

Overview

The WhatsApp functions are clearly explained, but automatic setup can execute unverified code and introduce broader agent changes without clear user control.

Review the setup before installing. Prefer a separately verified, fixed CLI release and explicitly approve local installation. Check whether its automatic skill synchronization will change other agents, and disable that behavior if unwanted. OOMOL mediates WhatsApp access, so consider the privacy of messages processed through it. Installer contents and the external runtime could not be verified.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command executes an Oomol-hosted installer rather than performing WhatsApp Chat API operations. Nothing in the chunk establishes this installer as a supporting dependency for the declared purpose. The downloaded script's contents are not supplied, so its further effects cannot be determined.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The supplied chunk only invokes a CLI login command; it contains no WhatsApp API operations or evidence that oo authenticates to chat-api.com. Authentication could be a supporting implementation detail if that relationship were established, but the supplied code does not establish it.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a mutable network response directly into Bash without pinning or verifying the script. HTTPS protects transport but does not prevent a compromised publisher or distribution endpoint from supplying malicious code; the legitimate CLI dependency explains the download but does not eliminate that supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

The fallback setup instructs the agent to execute downloaded installer scripts without warning the user about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback directs execution of downloaded shell or PowerShell code without a separate approval step or artifact verification. Although setup occurs only when the CLI is missing, a compromised installer source could execute arbitrary code with the agent's local privileges, and the write-confirmation rules cover WhatsApp changes rather than local installation.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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 83)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources