1.Gemini 4: A New Hopeblog | 2026-10-14 00:00 | tenzai.com | Original ↗ | .md | #llm-security | #review | #gemini
2.Building an AI Detection Engine That Understands Agent Intentblog | 2026-09-17 14:04 | wiz.io | Original ↗ | .md | #ai-security | #threat-detection | #llm-security
3.DavidCarliez/trustmebro: Bypass llm guardrails by confusing it with fabricated tool outputtool | 2026-09-02 23:54 | github.com | Original ↗ | .md | #ai-security | #open-source | #red-team
4.Beyond the Model: Benchmarking Codex Security, Claude Security, and Neburesearch | 2026-09-01 00:00 | nebusec.ai | Original ↗ | .md | #ai-security | #codex | #benchmark
5.Inside 90 days of attacks on AI infrastructureresearch | 2026-08-27 16:33 | wiz.io | Original ↗ | .md | #ai-security | #cloud | #rce
6.State divergence enables unauthorized accessblog | 2026-08-25 11:00 | blog.trailofbits.com | Original ↗ | .md | #web3 | #access-control | #vulnerability
7.Defeating AI-Assisted Reverse Engineering (or at Least Trying To)research | 2026-08-19 22:00 | blog.quarkslab.com | Original ↗ | .md | #ai-security | #vulnerability-research | #reverse-engineering
8.AI lectures with Dr. Brumley Part 5 | Defense using AI: The compliance clock is runningblog | 2026-08-20 12:00 | bugcrowd.com | Original ↗ | .md | #ai-security | #compliance | #llm-security
9.We burned 11.7bn tokens to find the best cyber AI modelblog | 2026-08-21 00:00 | aikido.dev | Original ↗ | .md | #ai-security | #open-source | #benchmark
10.Don’t Break the Agent: Lessons in Token Optimizationblog | 2026-08-20 16:30 | jfrog.com | Original ↗ | .md | #jfrog | #llm-security | #ai-agents
11.Testing AI-powered systems at scale via Bug Bounty, part 3: the guardrailsblog | 2026-07-29 07:06 | yeswehack.com | Original ↗ | .md | #ai-security | #bug-bounty | #featured
12.Suspected Chinese Operators Use Claude Code and DeepSeek to Breach Government Systems Across Four Countriesblog | 2026-07-14 00:00 | hunt.io | Original ↗ | .md | #ai-security | #agentic-ai | #claude-code
13.Build AI Security Agents with Wiz MCPblog | 2026-07-02 11:00 | wiz.io | Original ↗ | .md | #ai-security | #mcp | #llm-security
14.Tenzai Launches AI Application Testing, Chaining Vulnerabilities Across Web, API, and AI Surfacesblog | 2026-06-24 00:00 | tenzai.com | Original ↗ | .md | #ai-security | #web-security | #api-security
15.LLM SecRange: Open-Source Penetration Testing Playground for Large Language Models & Vulnerable Agentstool | 2026-06-20 08:06 | github.com | Original ↗ | .md | #ai-security | #rce | #ctf
16.The Smash-and-Grab Erablog | 2026-06-17 00:00 | bishopfox.com | Original ↗ | .md | #ai-security | #ransomware | #apt
17.Taking Maestro in Stride: AI Threat Modeling Frameworksblog | 2026-04-16 00:00 | bishopfox.com | Original ↗ | .md | #ai-security | #llm-security | #ai-agents
18.Responsible AI at HackerOne: 2026 Updateblog | 2026-04-09 13:48 | hackerone.com | Original ↗ | .md | #ai-security | #cloud | #agentic-ai
19.From Shai-Hulud to LiteLLM: Supply Chain Attackers Are Coming for Your Agentsblog | 2026-03-30 13:15 | jfrog.com | Original ↗ | .md | #ai-security | #supply-chain | #mcp
20.From Guardrails to Proof: Introducing Agentic Prompt Injection Testingblog | 2026-03-18 14:00 | hackerone.com | Original ↗ | .md | #ai-security | #agentic-ai | #red-teaming
21.Agentic Problems and the Rise of Zombie AIsresearch | 2026-02-17 00:00 | ethiack.com | Original ↗ | .md | #ai-security | #prompt-injection | #llm-security
22.AI Red Teaming Explained by AI Red Teamersblog | 2026-01-13 15:59 | hackerone.com | Original ↗ | .md | #ai-security | #attack-surface | #prompt-injection
23.Bishop Fox Wrapped: Research Worth Replayingblog | 2025-12-23 00:00 | bishopfox.com | Original ↗ | .md | #ai-security | #vulnerability-research | #social-engineering
24.Ready to Hack an LLM? Our Top CTF Recommendationsblog | 2025-11-05 00:00 | bishopfox.com | Original ↗ | .md | #ai-security | #ctf | #prompt-injection
25.3 Signals You Can’t Ignore from the 2025 Hacker-Powered Security Reportblog | 2025-11-04 15:24 | hackerone.com | Original ↗ | .md | #ai-security | #bug-bounty | #mcp
26.When AI Turns Criminal: Deepfakes, Voice-Cloning & LLM Malwareblog | 2025-10-31 00:00 | netlas.io | Original ↗ | .md | #ai-security | #malware | #phishing
27.Inside the AI Red Teaming CTF: What 200+ Players Taught Us About Breaking and Defending LLMsblog | 2025-10-23 14:36 | hackerone.com | Original ↗ | .md | #ai-security | #red-teaming | #ctf
28.Prompt injection to RCE in AI agentsblog | 2025-10-22 11:00 | blog.trailofbits.com | Original ↗ | .md | #ai-security | #rce | #prompt-injection
29.Prompt injection engineering for attackers: Exploiting GitHub Copilotblog | 2025-08-06 04:00 | blog.trailofbits.com | Original ↗ | .md | #ai-security | #prompt-injection | #llm-security
30.We built the security layer MCP always neededblog | 2025-07-28 11:00 | blog.trailofbits.com | Original ↗ | .md | #ai-security | #mcp | #prompt-injection