1.How We Built an Autonomous AI Security Triager: From LLM to 20,000+ Real Reportsblog | 2026-10-22 10:24 | hackenproof.com | Original ↗ | .md | #ai-security | #bug-bounty | #automation
2.How abliterated models can get you pwnedresearch | 2026-10-07 23:47 | projectdiscovery.io | Original ↗ | .md | #bug-bounty | #supply-chain | #prompt-injection
3.PIChef. A tool for Prompt Injection inspired by CyberChefblog | 2026-10-08 11:31 | blog.sentry.security | Original ↗ | .md | #prompt-injection | #llm | #tooling
4.Request, Aggregate, Bypass: How Attackers Can Evade LLM Safety Classifiersblog | 2026-10-06 00:00 | crowdstrike.com | Original ↗ | .md | #ai-security | #llm | #crowdstrike
5.Introducing Adversary Intelligence: LLM Tradecraftblog | 2026-09-30 11:30 | specterops.io | Original ↗ | .md | #ai-security | #threat-intelligence | #llm
6.Five Models Walk Into an App Builder. Security Gets Interesting.blog | 2026-09-30 00:00 | tenzai.com | Original ↗ | .md | #ai-security | #benchmark | #llm
7.Security Review for AI-Generated Code: What Changes Before Mergeblog | 2026-09-28 15:05 | borghq.io | Original ↗ | .md | #ai-security | #appsec | #code-review
8.You Can't Ask Attackers to Slow Downblog | 2026-09-28 00:00 | tenzai.com | Original ↗ | .md | #ai-security | #llm | #ai-policy
9.Bypassing EDR with Local AIblog | 2026-09-24 02:34 | projectblack.io | Original ↗ | .md | #ai-security | #windows | #penetration-testing
10.AI for Offensive Security: What Works, What Does Not, and How to Adopt Itblog | 2026-09-24 16:00 | specterops.io | Original ↗ | .md | #ai-security | #red-team | #offensive-security
11.Optimize your team's price-performance with hosted open weight modelsblog | 2026-09-17 00:00 | about.gitlab.com | Original ↗ | .md | #gitlab | #llm | #ai-models
12.Build It or Buy It? An Evidence-Based Framework for AI Security Testingblog | 2026-09-21 08:35 | projectdiscovery.io | Original ↗ | .md | #ai-security | #bug-bounty | #devsecops
13.When to use SAST versus an LLM security scannerblog | 2026-09-16 00:00 | about.gitlab.com | Original ↗ | .md | #ai-security | #appsec | #devsecops
14.PhantomRaven: An LLM-Generated Information Stealer Developed for Bug Bounty Huntingresearch | 2026-09-15 00:00 | crowdstrike.com | Original ↗ | .md | #ai-security | #bug-bounty | #supply-chain
15.AI Application Security Testing: The Authorisation Boundaryblog | 2026-09-14 15:50 | borghq.io | Original ↗ | .md | #ai-security | #appsec | #llm
16.CrowdStrike Accelerates Real-Time Data Classification with On-Device AIblog | 2026-09-16 00:00 | crowdstrike.com | Original ↗ | .md | #ai-security | #cloud | #data-security
17.ReAgent: Open-Source AI Agent for Autonomous Binary Reverse Engineering and C/C++ Reconstructiontool | 2026-09-09 20:35 | github.com | Original ↗ | .md | #ai-security | #open-source | #red-team
18.Living off Someone Else's Inferenceblog | 2026-09-09 11:22 | blog.sentry.security | Original ↗ | .md | #ai-security | #reconnaissance | #llm
19.GPT-6 Astra on GitLab: Faster runs, fewer tokens usedblog | 2026-09-08 00:00 | about.gitlab.com | Original ↗ | .md | #gitlab | #benchmark | #ai-agents
20.Bring your own model to GitLab Duo Self-Hosted with Microsoft Foundryblog | 2026-09-08 00:00 | about.gitlab.com | Original ↗ | .md | #ai-security | #gitlab | #llm
21.llama.cpp: High-Performance Open-Source LLM Inference in C/C++tool | 2026-09-06 22:10 | github.com | Original ↗ | .md | #ai-security | #open-source | #llm
22.How to use Codex for Bug Bounty research: explore broadly, validate rigorouslyblog | 2026-09-03 07:04 | yeswehack.com | Original ↗ | .md | #bug-bounty | #vulnerability-research | #codex
23.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
24.Robin: AI-Powered Dark Web OSINT & Threat Intelligence Investigation Tooltool | 2026-08-25 00:38 | github.com | Original ↗ | .md | #ai-security | #open-source | #threat-intelligence
25.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
26.Introducing EchoBench: A Human Calibrated Benchmark for Autonomous Pentestingblog | 2026-08-21 00:00 | netspi.com | Original ↗ | .md | #ai-security | #pentesting | #agentic-ai
27.Strategy is Key: Evaluating the Pentesting Skills of Frontier LLMsresearch | 2026-08-19 00:00 | ethiack.com | Original ↗ | .md | #ai-security | #pentesting | #benchmark
28.From chaos to context: Building an AI dev workflowblog | 2026-08-19 19:01 | about.gitlab.com | Original ↗ | .md | #ai-security | #gitlab | #browser-security
29.Don’t Break the Agent: Lessons in Token Optimizationblog | 2026-08-20 16:30 | jfrog.com | Original ↗ | .md | #jfrog | #llm-security | #ai-agents
30.Using Genius AI Models for Important Things: Cheating at NetHackblog | 2026-08-20 04:00 | josephthacker.com | Original ↗ | .md | #ai-security | #vulnerability-research | #llm