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
Adversa AI Trusted AI Blog · August 18, 2026

Top 10 zero-click attacks against AI agents

analysis Prompt InjectionAgent SecurityAI Red Teaming
Why it matters

Adversa compares ten shipped or research-stage zero-click agent compromises, including EchoLeak, DuneSlide, TrustFall, ShadowLeak, GeminiJack, and Morris II. The recurring chain is untrusted retrieved content entering model context, an agent applying inherited privileges, and data or code escaping through images, cloud requests, browser navigation, email, or a developer shell.

My takeaway: Classify email, documents, search results, MCP responses, and form fields as untrusted inputs to a privileged process. Give the agent a narrower identity than the user, log retrieval, memory writes, tool calls, and egress at runtime, restrict outbound destinations, and test the whole event chain instead of treating an approval dialog as a sufficient control.
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.

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.