near-ai-cloud
Verify NEAR AI Cloud Private Inference
Private AI deployments need proof that prompts and responses stay inside trusted hardware. This skill guides NEAR AI Cloud integration, attestation checks, and signed response verification.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "near-ai-cloud" from https://skillstore.io/skills/internet-court-near-ai-cloud.md and its manifest at https://skillstore.io/api/skills/internet-court-near-ai-cloud/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "near-ai-cloud". I need to add NEAR AI Cloud to an existing OpenAI SDK integration.
Expected outcome:
The skill returns a concise migration plan with the NEAR base URL, credential placement, model selection, and verification follow-up.
Using "near-ai-cloud". I need to confirm a model runs inside trusted hardware.
Expected outcome:
The skill produces an attestation checklist covering fresh nonces, NVIDIA result fields, Intel TDX quote validation, and signer matching.
Using "near-ai-cloud". I need to choose between private and anonymised models.
Expected outcome:
The skill summarizes model options by privacy type, context size, cost, and recommended workloads.
Security Audit
SafeAll 64 static detections occur in documentation examples or endpoint references. The examples intentionally use the NEAR AI Cloud API, environment-based API keys, and local nonce generation; no credential exfiltration, arbitrary command execution, or prompt-injection text was found.
Risk Factors
โ๏ธ External commands (19)
๐ Network access (28)
๐ Env variables (9)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/internet-court-near-ai-cloud/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/internet-court-near-ai-cloud?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/internet-court-near-ai-cloud?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/internet-court-near-ai-cloud/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/internet-court-near-ai-cloud.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA ยท BibTeX ยท CFF)
APA citation
internet-court. (2026). near-ai-cloud security audit report (audit version 2) [Author version 1.0.0]. Skillstore. https://skillstore.io/skills/internet-court-near-ai-cloud/audits/2BibTeX citation
@techreport{internet-court-internet-court-near-ai-cloud-2026,
author = {internet-court},
title = {near-ai-cloud security audit report (audit version 2)},
institution = {Skillstore},
year = {2026},
number = {2},
url = {https://skillstore.io/skills/internet-court-near-ai-cloud/audits/2},
note = {Author version 1.0.0}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "near-ai-cloud security audit report (audit version 2)"
version: "1.0.0"
type: report
authors:
- name: "internet-court"
date-released: "2026-07-21"
url: "https://skillstore.io/skills/internet-court-near-ai-cloud/audits/2"
identifiers:
- type: other
value: "skillstore:internet-court-near-ai-cloud:audit:2"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Build Private AI Features
Application developers can route OpenAI-compatible clients to NEAR AI Cloud while preserving private inference requirements.
Audit TEE Attestation
Security engineers can review nonce handling, NVIDIA NRAS fields, Intel TDX checks, and signing address binding.
Choose Cloud Models
Product teams can compare private and anonymised models for cost, context size, privacy, and capability fit.
Try These Prompts
Show me how to configure an OpenAI-compatible client for NEAR AI Cloud. Use the base URL and a placeholder API key.
Compare the listed NEAR AI Cloud models for my coding assistant. Explain privacy type, context size, cost, and task fit.
Create a verification checklist for a model attestation response. Include nonce freshness, NVIDIA NRAS fields, Intel TDX checks, and signing address binding.
Design an end-to-end trust flow for private chat responses. Include attestation, message signatures, replay protection, and operational failure cases.
Best Practices
- Generate a fresh random nonce for every attestation request.
- Verify both GPU attestation and Intel TDX evidence before trusting signatures.
- Store API keys in environment variables or a secret manager.
Avoid
- Treating an OpenAI-compatible response as private without attestation checks.
- Reusing old attestation reports after nonce or token expiration.
- Selecting models by name without checking privacy type and cost.
Frequently Asked Questions
Does this skill call NEAR AI Cloud by itself?
Which tools can use this skill?
Does it include complete verifier code?
What credentials are needed?
Can it verify chat signatures?
Is every model private?
Developer Details
Author
internet-courtLicense
MIT
Author version
v1.0.0
Skillstore revision
r1
Repository
https://github.com/internet-court/internet-court-skill/tree/main/vendored/near/near-ai-cloudRef
3f6e026a3363e0954ede7bef0cfe88d4475de137
Maintenance freshness
7/21/2026
Usage
1 downloads ยท 0 views
File structure