The Open Secure AI Alliance, now over 120 organizations, released SAFE guidelines at Black Hat to strengthen agentic AI
Members of the Open Secure AI Alliance are developing new guidelines to strengthen agentic AI cybersecurity as the annual Black Hat conference begins in Las Vegas. The Linux Foundation today shared a Request for Comments on Shared AI Findings Exchange, or SAFE, a proposed set of guidelines designed to turn agentic cybersecurity incidents into shared protection for the entire ecosystem.
The SAFE guidelines are being drafted by an Open Secure AI Alliance working group. NVIDIA, Cisco, CrowdStrike, Hugging Face and Red Hat are among Open Secure AI Alliance members working with the Linux Foundation to contribute to the initial proposal.
The SAFE guidelines include proposals to confidentially collect and analyze AI incidents and near misses, inform those impacted, identify recurring control failures and publish evidence-based operating recommendations that reduce systemic risk. The framework reflects the principle that cybersecurity requires rapid collective defense. When trusted ecosystems share threat intelligence openly, collective defense becomes a force multiplier. An AI agent is not just a model but a complete system—identity controls, harnesses, guardrails, logs and evaluation—and securing it requires more than vulnerability scanning.
NVIDIA's contributions run the length of the stack, starting with the NOOA research harness on GitHub, which makes agent behavior easier to test, trace, audit and govern. The NVIDIA OpenShell runtime restricts what an agent can see, touch and do by enforcing security and privacy controls at the agent level. NVIDIA's open model families—Nemotron for agentic AI, Cosmos for physical AI, Isaac GR00T for robotics, BioNeMo for healthcare and life sciences, and Alpamayo, the world's largest model for autonomous vehicles licensed for commercial use—ship with open weights, datasets and training techniques. NVIDIA open source verified agent skills provide portable instruction sets that are cataloged, scanned for risks such as prompt injection and tools poisoning, cryptographically signed and documented with a skill card. NeMo Guardrails, NeMo Anonymizer and NeMo Safe Synthesizer help enforce safety policies, protect sensitive data and generate privacy-safe synthetic data. Garak, NVIDIA's open source LLM vulnerability scanner, lets security teams check models for data leaks, prompt injections and jailbreak scenarios before they ship.
Other members are building across the defensive stack. Okta is developing reference implementations for agent identity and access using Cross App Access, an open protocol enabling AI agents operating in OpenShell sandbox environments to securely connect to enterprise applications. Palo Alto Networks has contributed open source tools from Idira including Agent Guard and Agent Watch to help developers apply identity security best practices. Red Hat founded asago, which maps an organization's custom governance requirements—such as those referenced in NIST, OWASP and the EU AI Act—directly to what agents are allowed to do at runtime with a single audit trail from policy clause to live control.
Amazon, which today became one of the newest members of the Open Secure AI Alliance, contributes Strands Agents, an open source toolkit for building AI agents that gives developers full visibility into agent behavior. Amazon also contributes Cedar, an open source authorization language that enforces deterministic, verifiable boundaries on what AI agents are permitted to do. Capital One open sourced VulnHunter for agentic AI code security. Cloudflare is offering its Vulnerability Discovery Harness as an open source skill to add security to agent systems. Microsoft AI Red Team has open sourced PyRIT, enabling AI red teamers to run automated red teaming with built in memory supporting common targets and custom endpoints. RAMPART turns red-team findings and real-world incidents into repeatable tests that run as software changes. Clarity helps teams question design assumptions and identify potential failures before code is written. Microsoft has also open sourced Assert, which converts natural language requirements and expected AI safety and security behaviors into executable evaluations. Atlas is Wiz's autonomous vulnerability research engine that orchestrates specialized AI agents to discover and validate security flaws across code and open source packages. Visa has also joined the Open Secure AI Alliance, contributing its open sourced Vulnerability Agentic Harness to help teams identify issues, support remediation and validation quickly and safely.
Specialized security and safety models are purpose-built for defense, trained to understand code, locate vulnerabilities and reason about threats at scale. Cisco DefenseClaw is an open source agentic governance layer that sits on top of NVIDIA OpenShell to provide robust automated security at the runtime level when scaling agentic workforces. Cisco has also released two of its Antares security small language models to help pinpoint where known vulnerabilities exist within a codebase and Project CodeGuard to embed secure-by-default practices directly into AI coding workflows. CrowdStrike is fine-tuning the NVIDIA Nemotron Nano model for cyber defense. Internal testing achieved 96 percent accuracy in generating investigation queries within Falcon LogScale, delivering a natural-language interface that boosts agent investigative efficiency.