ClawHub

Curity

Security checks across malware telemetry and agentic risk

Overview

This Curity skill appears legitimate, but it gives an agent broad authenticated control over an identity system without enough built-in limits or confirmation guidance.

Install only if you intend to let an agent operate through Membrane against a Curity environment. Prefer a test tenant or least-privileged account first, inspect available actions before use, require explicit approval for POST/PUT/PATCH/DELETE or administrative changes, and revoke the Membrane connection when finished.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The invocation description is overly broad: 'Manage data, records, and automate workflows' can cause the skill to be selected for generic enterprise tasks without clearly constraining Curity-specific identity-management operations. In a tool that can create connections and issue authenticated requests, over-triggering increases the chance of unintended access, data changes, or execution of sensitive actions in the wrong context.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill documents direct proxy requests to the Curity API, including arbitrary HTTP methods such as POST, PUT, PATCH, and DELETE, but does not warn that these calls can modify or delete live identity-system configuration and user/session data. Because Membrane injects authentication automatically, an agent could perform powerful state-changing operations with little friction if prompted ambiguously or maliciously.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal