ClawHub
Back to skill

Security audit

EngageLab SMS

Security checks across malware telemetry and agentic risk

Overview

This is a coherent EngageLab SMS helper, but it can send real SMS messages and modify or delete messaging resources without enough built-in confirmation or scoping guidance.

Install only if you intend to let an agent work with EngageLab SMS. Use limited-scope credentials where available, keep secrets out of shared logs and shell history, and require the agent to show recipients, message/template parameters, schedule times, and exact template or signature IDs before any live send, update, or delete.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill clearly enables outbound network access to a third-party SMS API but does not declare permissions or constraints for that capability. Missing permission declarations reduce transparency and policy enforcement, making it easier for an agent to invoke external actions without explicit governance or user awareness.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger text is broad enough to activate on generic terms like "sms api," "sender id," or integration requests, which may cause the skill to run in contexts beyond explicit EngageLab intent. Over-broad invocation increases the chance of unintended API guidance or destructive management actions being surfaced for the wrong task.

Tool Parameter Abuse

High
Category
Tool Misuse
Content
**Update** — `PUT /v1/template-configs/:templateId` (same body as create, all fields required)

**Delete** — `DELETE /v1/template-configs/:templateId`

## Signature (Sender ID) Management
Confidence
88% confidence
Finding
DELETE /v1/template-configs/:templateId`

Tool Parameter Abuse

High
Category
Tool Misuse
Content
**Update** — `PUT /v1/sign-configs/:signId` (same body as create)

**Delete** — `DELETE /v1/sign-configs/:signId`

## Generating Code
Confidence
88% confidence
Finding
DELETE /v1/sign-configs/:signId`

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal