From the Red Hat edition of November 10, 2026
SiliconANGLE/theCUBE (Red Hat-sponsored): Red Hat layers masked credentials, sandboxes and per-agent identity for AI agents; OpenShell still in preview and identity 'comes next'
SiliconANGLE Media / theCUBE (interview with Red Hat AI leaders) · Technology media; vendor interview · Global; recorded at KubeCon NA, Salt Lake City
- Publisher
- SiliconANGLE
- Original publication
- 2026-11-10
- Source retrieved
- 2026-11-11
- Event date
- 2026-11-10
What happened
Red Hat AI GM Joe Fernandes and chief architect Jessica Forrester describe layered agent security. With OpenShell, agents never receive real keys: credentials are masked on the way in and swapped on the way out. Agents can run in Kata Containers with their own kernels, in full VMs on OpenShift Virtualization, and behind network egress controls. Per-agent identity with least privilege 'comes next', integrating with identity systems. Red Hat is working with OpenAI on OpenClaw Enterprise to manage thousands of personal agents. OpenShell is available only in preview in Red Hat AI, and Fernandes says it is 'approaching' a stable milestone before Red Hat would rely on it for enterprise production.
Why it matters
Agencies and universities piloting coding or operations agents need credential isolation and per-agent identity before agents touch eligibility, student or public-safety systems. This source shows those controls are partly preview and partly roadmap, which helps set expectations for public-sector pilots.
Evidence and measured results
Opened the full write-up (updated 14:42 EST, 10 Nov 2026), with disclosure that Red Hat sponsored the segment. The claims are statements from executives, with no tests or customers. As a cross-check, I opened Checkable AI's independent Red Hat AI controls page (last checked 4 Nov 2026), which records no supported per-agent identity and OpenShell as Developer Preview.
Limitations and uncertainty
Sponsored vendor interview. OpenShell maturity is preview, and identity features are forward-looking. The independent cross-check is from before this edition's window and is used only to confirm current support status.
Put this evidence to work
Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-11-10; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.
Sales
Role takeaway
- Customer problem
- SLED teams piloting AI agents need credential isolation and attribution before connecting agents to sensitive systems.
- Stakeholders
- CISO
- Enterprise architect
- Research computing or DevOps lead
- Identity and access management team
- Discovery questions
- Which systems would agents touch, and with which credentials today?
- Can you accept preview-status sandboxing for a pilot?
- How would you attribute agent actions without per-agent identity?
- Value hypothesis
- Bounded: credential masking and sandboxing may reduce damage from compromised agents in pilots.
- Potential engagement
- A sandboxed agent pilot with red-team testing of credential leakage and egress controls.
- Unsupported claims
- Production-ready OpenShell
- Supported per-agent identity today
- Prevention of all prompt-injection harm
Pre-sales engineering
Role takeaway
- Fit
- Good for early agent pilots on OpenShift; not yet a supported production control set.
- Architecture and integration
- OpenShell credential brokering plus Kata Containers or OpenShift Virtualization VMs and egress policy.
- Prerequisites
- OpenShift with sandboxed containers or Virtualization
- Red Hat AI with OpenShell preview
- Egress allow-list design
- Constraints
- OpenShell is preview
- Per-agent identity is roadmap
- Sponsored-source claims untested
- Security
- Validate that real secrets never enter the agent context; log all credential swaps and egress attempts.
- Proof of value
- Prompt-injection test attempting key exfiltration
- Egress test to unapproved domains
- Attribution test of agent actions in audit logs
Delivery
Role takeaway
- Work
- Stand up a sandboxed agent pilot and red-team its controls.
- Dependencies
- Preview feature access
- Security team participation
- Non-production test systems
- Ownership
- Platform engineering with security office co-ownership.
- Skills and adoption
- Security staff learn sandbox policy authoring and agent threat modeling.
- Governance checkpoints
- Threat model review
- Red-team results review
- Decision gate before any production data
- Acceptance criteria
- Proposed: zero real credentials observed in agent context during tests
- Proposed: all unapproved egress attempts blocked and logged
- Risks
- Preview instability
- Weak attribution of agent actions
- Over-reliance on roadmap features
Implementation considerations
Lighthouse Advisory interpretation across the operating dimensions a public-sector buyer must settle before this evidence becomes a design. Each note answers the question under its heading for this specific source.
Architecture and integration
What must connect, and where does the AI sit in the workflow?
Credential brokering by the sandbox plus VM-level isolation (Kata/OpenShift Virtualization) and egress control form a defense-in-depth stack. Identity-system integration for agents is future work.
Governance
Who approves, reviews and stays accountable for outcomes?
Agent pilots should record which isolation layer each agent runs in and treat per-agent identity as unavailable in supported form today.
Security and privacy
What data, permissions and controls need testing?
Masked credentials reduce the impact of prompt-injected key leakage if the swap point is trustworthy. Without supported per-agent identity, audit attribution of agent actions may fall back to shared service accounts.
Accessibility and workforce
Who is affected, and what skills or accommodations follow?
Security teams will need new skills to run sandbox policy, egress rules and future agent identity integration.
Procurement
What should contracts, pricing and exit terms secure?
Do not buy agent platforms on the assumption of supported per-agent identity or GA OpenShell. Require roadmap commitments in writing if those features are essential.
Operating model
Which teams own the service once it runs?
Define who owns agent sandbox policies (platform vs security team) and how credential-swap rules are reviewed.
Publication history
- 2026-11-10Red Hat · Issue 116 resources
Stable resource ID: siliconangle-red-hat-agent-security-masked-keys-openshell-preview-20261110