Inworld Ai

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

Overview

This is a coherent Inworld AI integration, but it gives an authenticated agent broad action and direct API access with limited guardrails for write or delete operations.

Install only if you are comfortable connecting Membrane to your Inworld AI account. Before letting the agent run write/delete actions, manage users or API keys, or use the raw proxy, review the exact target and operation. Consider pinning/reviewing the Membrane CLI version instead of relying on @latest, and revoke the Membrane/Inworld connection when finished.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (1)

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The skill description is broad enough that an orchestrator could invoke it for generic 'manage data' or 'automate workflows' requests that are not clearly specific to Inworld AI. This can cause overbroad tool selection and unintended access or actions against a connected external service, especially when the skill supports both action execution and raw proxied API requests.

VirusTotal

65/65 vendors flagged this skill as clean.