Black Hat · July 29, 2026

From Prompt Tricks to Autonomous Hackers

video AI Red Teaming Agent Security Model Evaluation

From Prompt Tricks to Autonomous Hackers video thumbnail

Why it matters

Ari Herbert-Voss reviews three years of progress in autonomous offensive-security systems, evaluates where they can already complete meaningful attack tasks, and separates those capabilities from work that still needs human expertise. The talk frames scalable, parallel attack simulation as a challenge to point-in-time testing rather than as a product announcement.

My takeaway: Measure autonomous offensive systems by verified task completion, time, cost, false positives, and required human intervention. Use the resulting evidence to choose bounded continuous-testing workloads, preserve expert review for ambiguous findings, and prevent automated attack paths from reaching unauthorized targets.

Keep exploring

More curated notes connected through AI Red Teaming and Agent Security.

OpenAI News · framework

OpenAI’s Frontier Governance Framework

OpenAI's 22-page Frontier Governance Framework maps its frontier-model processes to California's Transparency in Frontier AI Act and the EU AI Act's general-purpose AI code. It documents lifecycle risk assessment, cyber-offense and other risk tiers, mitigation and residual-risk decisions, critical-incident handling, security risk management, model reporting, external review, responsibility allocation, and change control.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.

OECD.AI Wonk · guide

A five-step roadmap to closing the AI evaluation gap

The roadmap addresses evaluation results that overstate real-world performance or fail to transfer across deployment contexts. Its five steps balance standardized and local tests, evaluate throughout the lifecycle, build qualified assurance and communication capacity, tailor tests to each value-chain actor and technology, and use a coordinated, trusted process for updating methods.