ClawHub
Back to skill

Security audit

Attio

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Attio CRM API helper that can read and change CRM data through Maton, with no hidden code or install-time behavior found.

Install this only for Attio workspaces you intend the agent to access. Keep MATON_API_KEY private, verify the selected Maton connection when multiple accounts exist, and approve write/delete actions only after checking the exact target and effect. Treat CRM notes, meetings, and call recordings as sensitive data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The activation guidance is very broad, covering generic CRUD and query actions over CRM data without narrowing when the skill should be invoked or requiring confirmation for sensitive reads. In an agent setting, this increases the chance the skill is selected for requests involving sensitive customer data, expanding unintended data access and action surface.

Missing User Warnings

Medium
Confidence
81% confidence
Finding
The skill advertises access to meetings and call recordings, which can contain highly sensitive business and personal information, but it does not pair that capability with a prominent privacy warning or consent requirement for retrieval. In agent workflows, this omission can normalize access to sensitive artifacts without clear user awareness.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.