Ravi inbox

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says, but it gives an agent direct access to OTPs, verification links, and full inbox messages without clear handling guardrails.

Install only if you want an agent to read Ravi SMS and email for verification workflows. Treat OTPs, magic links, verification URLs, phone numbers, and email bodies as sensitive secrets; avoid displaying, logging, storing, forwarding, or reusing them unless the user explicitly requested that specific action.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: This skill exposes highly sensitive inbox data, including OTPs, verification links, phone numbers, email addresses, and full message bodies, but the description and notes do not prominently warn users about the sensitivity of this content. That omission increases the risk of accidental disclosure, unsafe logging, or misuse by downstream agents and operators, especially because the examples explicitly show OTP extraction and full-content retrieval.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal