NDC Conferences YouTube · March 23, 2026

Hijacking Google's CI/CD Through Prompt Injection: The New Era of AI-Based Exploits - Mackenzie Jackson

Hijacking Google's CI/CD Through Prompt Injection: The New Era of AI-Based Exploits - Mackenzie Jackson video thumbnail
Why it matters

NDC Security 2026 talk on prompt injection in CI/CD and automation systems, including AI agents with access to shell commands, GitHub or GitLab tokens, issue editing, build workflows, and privileged pipeline context.

My takeaway: Hijacking Google's CI/CD Through Prompt Injection: The New Era of AI-Based Exploits - Mackenzie Jackson is a prompt-injection signal. The practical read is to threat model prompt injection as an execution and credential-exposure path when agents are wired into trusted automation.
Keep exploring

More curated notes connected through Prompt Injection and Agent Security.

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.

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.

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.