Ory

• Outcome: Review
• Latest audit: May 29, 2026 at 9:37 PM UTC
• Version:
  1.0.2

Overview

This ORY integration appears legitimate, but it gives an agent broad authenticated access to identity-management APIs without enough guardrails for changes or deletions.

Review before installing. Use a least-privilege ORY/Membrane connection, confirm every state-changing action before it runs, avoid using raw proxy requests unless necessary, and revoke the Membrane/ORY access when finished.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The skill description is broad enough to match generic 'manage data, records, and automate workflows' requests, which can cause the agent to invoke this ORY integration outside clearly identity-related tasks. In the context of an IAM platform, accidental invocation is more dangerous because available actions may expose or modify authentication, session, OAuth client, or token-related resources.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The proxy request section explains how to send arbitrary HTTP methods, headers, body data, and path parameters directly to the ORY API, but does not warn that these calls can create, alter, or delete live identity and auth data. Because ORY manages sensitive IAM resources, unrestricted raw request guidance increases the chance of destructive or unsafe actions being performed without confirmation or guardrails.

VirusTotal

63/63 vendors flagged this skill as clean.