AI Red Team Engineering notes, research references, and field notes on AI systems, responsible AI, governance, and compliance.
Global search

Search AI Red Team

Search across the complete knowledge base.

Enter at least two characters to begin.
↑↓ select Enter open Browse the full research archive
The Hacker News AI Security · August 27, 2026

Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers

analysis Prompt InjectionAgent SecurityAI Red Teaming
Why it matters

Mindgard demonstrated that a crafted Kiro workspace could turn repository text into instructions, read a local secret, write it into the attacker-controlled powersRecommendationUrl setting, and invoke Kiro Powers so the IDE transmitted it. The chain affected trusted and untrusted workspaces in Kiro 0.7.45 and was fixed in 0.8.140.

My takeaway: Update Kiro and treat repository names, guidance files, workspace settings, and tool metadata as untrusted. Prevent agents from silently changing execution- or network-sensitive configuration, require confirmation for new destinations with resolved arguments, restrict reads of secrets, and test the complete content-to-agent-to-configuration-to-request chain.
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

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.