ClawHub
Back to skill

Security audit

MSG91

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent MSG91 connector, but one OTP resend action is treated like a safe read even though it can send messages through the user's account.

Review the action and payload before allowing this skill to send or resend OTPs or SMS messages. Treat `resend_otp` as a write action even though the skill does not label it that way, and only install the oo CLI from OOMOL if you trust that provider and intend to connect your MSG91 account.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The description says to use this skill for "ANY MSG91 request" and "instead of calling the API directly," which is an overly broad routing rule. That can cause an agent to invoke the skill for all MSG91-related tasks without evaluating least-privilege, alternative safer paths, or whether the request is appropriate, increasing the chance of unintended writes such as OTP sends or resend actions.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.