dan_l2

AI Leak Watch: 435,608 potential AI API key matches in public GitHub code

Posted by dan_l2 on Sunday May 17, 2026 @10:37PM
from the ai-keys-leaks.begimher.com dept.

https://ai-keys-leaks.begimher.com/

( Read More... | no comments | 5 points | on HN )

Re:Show HN: Armorer – A secure local control plane for AI agents on Thursday May 07, 2026 @11:33PM (#48058204)

Love the idea! I'm going to give it a try

Re:Sir-Bench – benchmark for security incident response agents on Thursday April 16, 2026 @04:14PM (#47798876)

Authors here. Existing security-AI benchmarks measure knowledge, offensive capability, or workflow completion. SIR-Bench measures whether an agent discovers novel evidenceduring an investigation vs. reaching the right conclusion by restating the alert. 794 test cases derived from 129 real incident patterns, replayed in live cloud environments. Happy to answer questions on methodology, scoring, or failure modes we saw acrossfrontier models.

Sir-Bench – benchmark for security incident response agents

Posted by dan_l2 on Thursday April 16, 2026 @04:14PM
from the arxiv.org dept.

https://arxiv.org/abs/2604.12040

( Read More... | 2 comments | 3 points | on HN )

AWS Security Incident Response now provides agentic AI-powered investigation

Posted by dan_l2 on Saturday November 22, 2025 @07:08PM
from the aws.amazon.com dept.

https://aws.amazon.com/blogs/security/accelerate-investigations-with-aws-security-incident-response-ai-powered-capabilities/

( Read More... | no comments | on HN )