1.Post-Mortem of Misaligned OpenAI Modelresearch | 2026-10-17 02:40 | projectdiscovery.io | Original ↗ | .md | #bug-bounty | #ai-safety | #openai
2.Is AI pentesting safe?blog | 2026-09-24 07:16 | yeswehack.com | Original ↗ | .md | #ai-security | #ai-safety | #penetration-testing
3.VMs won't contain cyber-capable agentsblog | 2026-08-26 11:00 | blog.trailofbits.com | Original ↗ | .md | #ai-security | #cloud | #zero-day
4.Could OpenClaw have actually hacked that Australian gym? We decided to test it.blog | 2026-08-25 00:00 | aikido.dev | Original ↗ | .md | #ai-security | #ai-safety | #aikido
5.Engineering the Impossible: Adding Safety to Autonomous Agentsblog | 2026-08-12 12:00 | xbow.com | Original ↗ | .md | #ai-safety | #sandboxing | #offensive-security
6.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
7.What is AI harness engineering?blog | 2026-08-06 00:00 | aikido.dev | Original ↗ | .md | #ai-security | #agentic-ai | #ai-safety
8.Secure Agent Harness Execution: Preventing Escapeblog | 2026-08-04 00:00 | crowdstrike.com | Original ↗ | .md | #ai-security | #agentic-ai | #ai-safety
9.The OpenAI and Hugging Face Incident: When the Model Hacks the Testresearch | 2026-07-22 13:21 | xbow.com | Original ↗ | .md | #ai-security | #zero-day | #featured
10.Grok 4.5 Is Powerful. The System Around It Makes It Safe.blog | 2026-07-31 12:00 | xbow.com | Original ↗ | .md | #ai-security | #pentesting | #agentic-ai
11.CrowdStrike Joins the Open Secure AI Alliance to Advance AI Safety and Securityblog | 2026-07-27 00:00 | crowdstrike.com | Original ↗ | .md | #ai-security | #vulnerability-research | #open-source
12.AI lectures with Dr. Brumley Part 2 | The anatomy of a modern AI systemblog | 2026-07-23 12:00 | bugcrowd.com | Original ↗ | .md | #ai-security | #supply-chain | #ai-safety
13.Here’s How an OpenAI Model Went Rogue and Hacked Hugging Faceblog | 2026-07-23 00:00 | hacktron.ai | Original ↗ | .md | #agentic-ai | #ai-safety | #threat-intelligence
14.Testing AI-powered systems at scale via Bug Bounty, part 2: AI-specific vulnerabilitiesblog | 2026-07-15 07:11 | yeswehack.com | Original ↗ | .md | #ai-security | #bug-bounty | #agentic-ai
15.Launching: AI Safety For Parentsblog | 2026-06-30 00:00 | josephthacker.com | Original ↗ | .md | #ai-security | #zero-day | #ai-safety
16.Full Fathom Five: The context of Anthropic’s Mythos-class public releaseblog | 2026-06-13 00:00 | aikido.dev | Original ↗ | .md | #ai-security | #vulnerability-management | #ai-safety
17.Security metamorphosis: a Mythos-ready architecture checklist for autonomous AI attacksblog | 2026-05-05 00:00 | aikido.dev | Original ↗ | .md | #ai-security | #cloud | #agentic-ai
18.We Ran 1,060 Autonomous Attacks. Here's What the Industry Gets Wrong.blog | 2026-03-02 13:00 | xbow.com | Original ↗ | .md | #ai-security | #vulnerability-research | #ai-safety
19.International AI Safety Report 2026: What It Means for Autonomous AI Systemsblog | 2026-02-09 00:00 | aikido.dev | Original ↗ | .md | #ai-security | #agentic-ai | #ai-safety
20.Can chatbots craft correct code?blog | 2025-12-19 12:00 | blog.trailofbits.com | Original ↗ | .md | #ai-security | #ai-safety | #llm
21.The AI Security Playbook: Match Your Testing to Your Maturityblog | 2025-11-20 20:04 | hackerone.com | Original ↗ | .md | #ai-security | #ai-safety | #prompt-injection
22.AI Security vs. AI Safety: Two Pillars CISOs Must Operationalizeblog | 2025-11-18 15:08 | hackerone.com | Original ↗ | .md | #ai-security | #ai-safety | #risk-management
23.AI Comprehension Gaps: When Humans and AI See Different Thingsblog | 2025-09-24 00:00 | josephthacker.com | Original ↗ | .md | #ai-security | #ai-safety | #llm
24.AI Models Are Not Safety-Tuned for Kidsblog | 2025-08-19 00:00 | josephthacker.com | Original ↗ | .md | #ai-security | #ai-safety | #llm
25.Introducing the Glazing Score 🍩blog | 2025-04-30 00:00 | josephthacker.com | Original ↗ | .md | #ai-security | #ai-safety | #benchmark
26.AI Bias: Consequences and Mitigationblog | 2025-04-18 17:23 | hackerone.com | Original ↗ | .md | #ai-security | #ai-safety | #machine-learning
27.Safe harbor and the future of AI flaw reporting: Lessons from vulnerability disclosurevulnerability | 2025-03-13 18:26 | bugcrowd.com | Original ↗ | .md | #ai-security | #cloud | #ai-safety
28.HackerOne Joins Call for Action on AI Third-Party Evaluation and Flaw Disclosureblog | 2025-03-12 19:37 | hackerone.com | Original ↗ | .md | #ai-security | #ai-safety | #ai-governance
29.How Anthropic’s Jailbreak Challenge Put AI Safety Defenses to the Testblog | 2025-03-03 18:48 | hackerone.com | Original ↗ | .md | #ai-security | #ai-safety | #red-teaming
30.A Partial Victory for AI Researchersblog | 2025-01-10 18:37 | hackerone.com | Original ↗ | .md | #ai-security | #ai-safety | #red-team