KVcore MCP CLI

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent KVcore CRM helper, but it exposes broad CRM-changing, outbound messaging, raw API, and Twilio call powers without enough scoping or user-control guidance.

Review before installing. Use only with trusted KVcore and Twilio accounts, least-privilege tokens, and explicit human confirmation before sending emails, texts, calls, changing contacts or tags, refreshing campaigns, or using raw API access. Verify the referenced MCP/CLI implementation source before giving it production credentials.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (2)

Missing User Warnings

Medium

Confidence: 87% confidence
Finding: The skill advertises the ability to send emails/texts, place calls, and use raw endpoint access, but it does not warn that these actions can transmit sensitive data externally or modify CRM records. In an agent setting, this increases the risk of unintended outbound communications, unauthorized record changes, or misuse of unrestricted API actions through `kvcore_request`.

Missing User Warnings

Low

Confidence: 78% confidence
Finding: The environment section lists live KVcore and Twilio credentials without any handling guidance, increasing the chance that operators or downstream agents treat them as ordinary inputs rather than secrets. While it does not directly expose secrets, the lack of warning can contribute to accidental disclosure in logs, prompts, screenshots, or misconfigured environments.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal