ClawHub
Back to skill

Security audit

Attio CRM CLI

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent Attio CRM helper, but users should treat its CRM credentials, write examples, and generated schema file carefully.

Before installing, inspect or pin the external attio-cli source, use a least-privileged Attio API key, keep the key out of shared or committed dotfiles, and treat generated workspace schema files as confidential. Only run the create-record or add-list-entry examples when you intend to modify the target CRM workspace.

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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly instructs users to generate a local markdown schema containing workspace objects, attributes, lists, and field options, which can expose sensitive internal CRM structure and business metadata if stored insecurely, committed to source control, or shared with other tools. In this context, the issue is not remote exploitation but unsafe guidance that encourages creation of a potentially sensitive artifact without any warning, access controls, or handling guidance.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The API examples include live write operations that create records and add list entries in a production CRM, but they are presented without any warning that they modify real workspace data. This increases the risk of accidental integrity-impacting actions, especially when users copy-paste examples assuming they are read-only reference commands.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.