ClawHub
Back to skill

Security audit

KVcore MCP CLI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a legitimate KVcore CRM helper, but it gives broad messaging, calling, and raw API access without enough user-control or secret-handling guidance.

Review this carefully before installing. Use least-privilege KVcore and Twilio credentials, keep secrets only in secure environment storage, and require explicit user confirmation before sending emails or texts, placing calls, changing contacts or tags, refreshing campaigns, or using raw API endpoints.

A.I.G

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

SkillSpector

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
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill advertises raw endpoint access plus email, text, and calling actions that can affect external parties, but it provides no safety guidance about confirmation, authorization, or the risk of transmitting contact data. In an agent context, this increases the chance of unintended outbound actions, privacy violations, or misuse of powerful CRM capabilities through overly broad user prompts.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The environment section lists live API and Twilio credentials without guidance on secret handling, storage, or operational risk from telephony and messaging features. While not a direct secret leak, this normalizes use of high-impact credentials without warning, which can contribute to accidental exposure, misuse, or unsafe deployment practices.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.