All articles
-
LLM Jailbreak Defense Techniques: A Practitioner's Guide
A technical breakdown of LLM jailbreak defense techniques, from input filtering and model-level hardening to multi-agent architectures and OWASP mitigations.
-
What a Good Weekly AI Security Newsletter Should Actually Cover
A working guide to evaluating a weekly AI security newsletter: what belongs in one, which primary sources it should cite, and how to spot vendor noise.
-
Prompt Injection Detection Tools: The 2026 Landscape for LLM Defenders
Prompt injection tops the OWASP LLM Top 10, and the tool market has consolidated fast. A field guide to Llama Prompt Guard 2, Azure Prompt Shields, Lakera Guard, NeMo Guardrails, and the open-source options that survived.
-
OWASP LLM Top 10 2026 Changes: What's New, Gone, and Coming
A practitioner breakdown of the OWASP LLM Top 10 2026 changes — two new threat categories dropped, three proposed additions for 2026, and a companion
-
AI Agent Security Risks 2026: Prompt Injection to Privilege Abuse
OWASP's Q1 2026 GenAI Exploit Round-up confirms AI agent security risks have moved from research to active production breaches.
-
LLM Prompt Injection Attack Examples: Direct, Indirect, Agentic
A practitioner-level breakdown of LLM prompt injection attack examples — from basic instruction overrides to CVE-rated zero-click exploits in production
-
AI Sec Weekly: Friday, May 22, 2026
This week's digest: SSRF through agent tool-use, the model supply-chain class and why safetensors matters, and model extraction as a business risk.
-
AI on the Offense: Google's Zero-Day Warning and LLM Jailbreaks
Google says it caught an attacker using an LLM to find a zero-day, peer-reviewed research shows reasoning models can autonomously jailbreak other models
-
How LLM Chatbots Leak Data Through Their Own Rendered Output
A recurring AI-security finding: an injected instruction makes the model emit a markdown image whose URL carries the user's data to an attacker server.
-
AI Sec Weekly: Friday, May 15, 2026
This week's digest: indirect injection becomes the agent-era default, the markdown-rendering data-exfiltration class, and why system-prompt secrecy keeps
-
LiteLLM SQL Injection (CVE-2026-42208) and the AI Gateway Risk
A pre-auth SQL injection in the LiteLLM proxy landed in CISA's KEV catalog and was exploited within roughly 36 hours of disclosure.
-
Indirect Prompt Injection: The Agent Era's Default Vulnerability
As LLM agents gained tools and memory, the dangerous injection stopped coming from the user and started coming from the data the agent reads.
-
The OWASP LLM Top 10 (2025) Changed More Than the Numbering
The 2025 revision of the OWASP Top 10 for LLM Applications added system-prompt leakage and vector/embedding weaknesses, and reframed the supply-chain
-
How AI Sec Weekly Works: The Format and Why It Looks This Way
Every Friday digest follows the same structure for a reason. Here's the format breakdown — three top stories, the reading list, and what gets left out.
-
Why AI Sec Weekly Is Weekly, and What Makes the Cut
AI Sec Weekly is a Friday roundup of AI security news. Here's the case for a seven-day cadence, the bar an item has to clear, and how each entry is written.