Tag feed

#llm-security

45 posts0 followers

Explore Hashnode

Alternatives

Trending tags this week

JJebitoksharonjebitok.com2d ago · 61 min read

Token City - AI Odyssey CTF (TryHackMe)

Link to the section of the AI Odyssey CTF on TryHackMe: Token City. It covers challenges like: ML Sec: The Loan Arranger | AI Sec + DFIR: Rogue Commit | AI Sec + Web App Sec: Sealed Substation | Agent

0

VNVũ Nhật Lâmblog.fiscybersec.com6d ago · 12 min read

Gemini's Secret Affair: Notification-Based Prompt Injection and the Fake Context Alignment Technique

A single WhatsApp message from an unknown number is enough to turn the Gemini voice assistant into an attacker's tool — opening the smart windows in a victim's home, live-streaming their video over Zo

0

MSManuela Schrittwieserneuralstackms.techJun 17 · 14 min read

RAG Under Fire: Retrieval Pipeline Vulnerabilities & Indirect Prompt Injection

NeuralStack | MS Tech Blog – Databases & Data Engineering in AI Security Engineering, Part 3 of 4 The Retrieval Pipeline as a Trust Boundary Retrieval-Augmented Generation (RAG) is now the dominant a

0

NDNAS Digitalnasdigital.hashnode.devJun 12 · 8 min read

Your Semantic Kernel Agent Has a CVSS 10.0 Vulnerability — And the Patch Doesn't Fully Fix It

On 7 May 2026, Microsoft disclosed two critical vulnerabilities in Semantic Kernel, the official .NET framework used to build AI agents and LLM-powered applications. One was assigned a CVSS score of 1

0

NPNarges Pourkamalisafeai.blogJun 8 · 8 min read

PortSwigger's Insights: Understanding Web LLM Attacks

PortSwigger has taken an important step towards understanding LLM attacks. I studied this topic and wrote down the key points to better understand it. 1. Fundamental Concepts Learn a little more about

4

LR

JAJoel A Pzyberjoe.hashnode.devJun 5 · 10 min read

How I Jailbroke an Autonomous AI Agent — Exposing 12 Tools, 23 API Actions, and Full Infrastructure Write Access

Severity: P0 · Critical · ResolvedTechnique: Multi-turn contextual prompt chainingVulnerability Chain: Broken Access Control → Indirect Prompt Injection (RAG Poisoning) → Agentic Tool AbuseResult: Per

0

AVAnvesh Vishwarajuanveshtheaisocanalyst.hashnode.devJun 3 · 10 min read

Why Single-Layer LLM Triage Is Dangerous in a SOC — And the Architecture I'm Building to Prevent It

Published on Hashnode | Anvesh Raju Vishwaraju | June 2026 I came across an article recently that genuinely surprised me. Not because the topic was new to me — but because someone at the same educatio

1

A

OOmnithiumomnithium.hashnode.devJun 1 · 16 min read

AI Agent Security: Defending Against Prompt Injection in Production

Prompt injection is not a theoretical concern. It is the most consistently exploited vulnerability class in production AI agent systems today, and the attack surface grows in direct proportion to how

0

NPNarges Pourkamalisafeai.blogMay 29 · 2 min read

AI Security is far more complex than just tricky prompts! 🚀

Recently, I started reviewing an incredible document: the "AI Security Assessment Blueprint". It has truly opened a new window of knowledge for me, answering so many of my deepest questions about AI v

0

NPNarges Pourkamalisafeai.blogMay 29 · 3 min read

Agentic AI Security—How can autonomous agents be hijacked to steal data?

You received a normal email. No malicious links. No suspicious attachments. But that single email was enough for your company's AI assistant to silently send all your confidential data to an attacker!

0

#llm-security

Search Hashnode

#llm-security

Explore Hashnode

Trending tags this week

Token City - AI Odyssey CTF (TryHackMe)

Gemini's Secret Affair: Notification-Based Prompt Injection and the Fake Context Alignment Technique

RAG Under Fire: Retrieval Pipeline Vulnerabilities & Indirect Prompt Injection

Your Semantic Kernel Agent Has a CVSS 10.0 Vulnerability — And the Patch Doesn't Fully Fix It

PortSwigger's Insights: Understanding Web LLM Attacks

How I Jailbroke an Autonomous AI Agent — Exposing 12 Tools, 23 API Actions, and Full Infrastructure Write Access

Why Single-Layer LLM Triage Is Dangerous in a SOC — And the Architecture I'm Building to Prevent It

AI Agent Security: Defending Against Prompt Injection in Production

AI Security is far more complex than just tricky prompts! 🚀

Agentic AI Security—How can autonomous agents be hijacked to steal data?