ClawHub

Attio

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Attio CRM reference skill, but users should protect the API key and approve any CRM write actions.

Install only if you intend to let an agent work with Attio CRM. Use a least-privilege Attio token, avoid committing or sharing `~/.env`, verify the `attio` CLI you run, and require explicit approval before creating or updating records, adding pipeline entries, creating notes/tasks, or completing tasks.

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
93% confidence
Finding
The skill advertises state-changing CRM operations such as creating notes and tasks without explicitly warning that these commands modify external business data. In an agent context, this increases the chance of unintended writes to live customer records, especially if a user expects read-only lookup behavior.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The setup instructions tell users to persist an Attio API key in environment files but provide no guidance on protecting the credential, limiting its scope, or avoiding accidental exposure. This can lead to credential leakage through shell history, shared home directories, checked-in dotfiles, or over-privileged tokens being used in automation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal