Black Hat · November 3, 2026

FSTab: test recurring security flaws across AI-generated application features

video AI Red Teaming Model Evaluation AI Engineering

FSTab: test recurring security flaws across AI-generated application features video thumbnail

Why it matters

The FSTab research maps visible application features to recurring static-analysis findings in code generated by a known model family. It builds model-specific tables from generated examples and tests transfer to held-out applications and domains. Reported attack success means overlap with scanner findings, not confirmed compromise; model identification, feature labeling and scanner errors limit the conclusions.

My takeaway: Build regression cases for authentication, uploads and other sensitive features across prompt variations and application domains. Keep construction examples separate from held-out tests and record the model and scanner versions. Use predicted vulnerability classes to prioritize code review and authorized dynamic checks, confirming reachability and impact before treating a scanner match as an exploitable flaw.

Keep exploring

More curated notes connected through AI Red Teaming and Model Evaluation.

OpenAI News · framework

Pacing model development in an era of cyber-critical capabilities

OpenAI says preliminary evidence that Astra may meet its Critical cybersecurity threshold led it to pause frontier reinforcement-learning work for two weeks and keep its largest planned run on hold. New safeguards include stronger workload and network isolation, continuous boundary testing, token-level monitoring that escalates suspicious tool activity, and broader alignment checks for deception, reward hacking, and unauthorized access.

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.

OpenAI News · framework

A blueprint for democratic governance of frontier AI

OpenAI proposes a three-part U.S. frontier-AI governance model: harmonize emerging state safety laws into a federal baseline, strengthen CAISI as an evaluation and standards institution, and coordinate a broader resilience program. Proposed controls include severe-risk evaluations, transparency reports, independent audits, safety-incident reporting, model-weight security, whistleblower protection, and periodic technical assessments.