Back to skill

Security audit

Vonage

Security checks for vulnerabilities and agentic risk

Overview

The Vonage actions have approval checks, but setup executes unverified remote code and under-discloses changes to other agent skills.

Review and install the CLI separately before using this skill, and disable startup skill synchronization if you do not want other agent skills added or refreshed. Confirm each SMS recipient, message, and potential charge. OOMOL mediates the connected account; its backend and the remote installer payloads were not verified in this review.

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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command executes an Oomol-hosted installer rather than performing the declared Vonage operations. Nothing in the supplied chunk establishes that this installation is a supporting dependency for Vonage functionality. The downloaded script's contents and further effects are not shown.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping a mutable remote installer directly into bash executes its contents without prior inspection, version pinning, or cryptographic artifact verification. HTTPS protects transport but does not protect against compromise of the publisher or distribution endpoint, which could yield arbitrary code execution under the user's account; the PowerShell alternative has the same risk.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

The setup workflow executes downloaded installation scripts without a warning about running remote code on the user's system.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback setup directs execution of downloaded shell or PowerShell scripts without explaining the local-code-execution risk or requiring explicit installation approval. Installation is conditional and relevant to the workflow, which reduces exposure, but a compromised installer could still execute arbitrary commands with the invoking user's privileges.

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 79)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