Beyond Pass/Fail: Using Process Mining to Understand How LLMs Resist (And Fail) Red Team Attacks

Standard AI red teaming evaluations reduce adversarial campaigns to a single binary outcome, attack success rate ASR, not taking into account the sequential structure of how models resist or yield to attacks. We propose applying process mining, a discipline for discovering and analyzing process...

Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us

In this article 1. Why the Taxonomy Needed Updating 2. Seven new failure modes 3. Operational findings: What red teaming showed 4. New mitigations 5. What to do this quarter When the Microsoft AI Red Team published the Taxonomy of Failure Modes in Agentic AI Systems in April 2025, the goal was a...

CVE-2026-35904

creationtimestamp| type| source ---|---|--- 2026-06-03 17:00:04+00:00| published-proof-of-concept| https://t.me/GithubRedTeam/87170 2026-06-03 19:00:30+00:00| seen| Telegram/Ze-uNkS3kIdAJGbWQE6AK--K-SMWz6YbrFE-sDGCdUicf4Q 2026-06-03 21:00:04+00:00| seen|...

CVE-2026-49943

creationtimestamp| type| source ---|---|--- 2026-06-03 06:00:04+00:00| seen| https://t.me/GithubRedTeam/87089 2026-06-03 07:00:16+00:00| seen| Telegram/o4hSLrg-DhwQDptmYynTF4BCpU3ri7L3EO654-e3xznsg0w 2026-06-03 09:00:04+00:00| seen| Telegram/5i-pTes7Ja8Uhuw9wP6auiAd2fWyZYO3DYvaqIbmREm4...

CVE-2026-8206

creationtimestamp| type| source ---|---|--- 2026-06-01 20:00:04+00:00| seen| https://t.me/GithubRedTeam/86883 2026-06-01 23:00:14+00:00| seen| Telegram/WmCsGmCxw3llm8l2PpPL4TbSd7NmUffJbXR2OZgq87qhTE 2026-06-02 04:30:27+00:00| seen| https://bsky.app/profile/offseq.bsky.social/post/3mnbr4mqu6h2j...

CVE-2026-49009

creationtimestamp| type| source ---|---|--- 2026-05-29 01:00:04+00:00| seen| https://t.me/GithubRedTeam/86315 2026-05-29 03:00:06+00:00| seen| Telegram/6s3VRd-d5V93Kqqbw2bpShp3KD9FSCashxK24K-SibeAsU 2026-05-29 03:00:14+00:00| seen| Telegram/Qn2Yw-Arqj9R5Yfut3fo2kk-MUMI5L3773Y6jZ-lhjERXA 2026-06-0...

-GodSearch

󰓾 GodSearch v20.0 — THE SOVEREIGN 💀 Universal Exploit Sear...

GodSearch

󰓾 GodSearch v20.0 — THE SOVEREIGN 💀 Universal Exploit Sear...

CVE-2026-27384

creationtimestamp| type| source ---|---|--- 2026-05-26 09:00:05+00:00| seen| https://t.me/GithubRedTeam/85938 2026-05-27 21:10:45+00:00| seen| Telegram/GF77XqZ1LHaWDL2kD1JemKeP32DvhHpTDQqckw5Eq33XXvc...

CVE-2026-36239

creationtimestamp| type| source ---|---|--- 2026-05-25 02:00:04+00:00| seen| https://t.me/GithubRedTeam/85759 2026-05-25 03:00:10+00:00| seen| Telegram/PWXxTbzLBS2I2NTEEZXYxWglH9J71PY-BvJO95sfjgRqY3E 2026-05-25 09:00:04+00:00| seen| Telegram/hq1WnakkbxJpSdatpwq9NAKRiUtHFa8ysgfQqaCqIO8mwqo...

rt-toolkit

Red Team Toolkit Curated operator catalog for red team enga...

CVE-2026-0211

creationtimestamp| type| source ---|---|--- 2026-05-22 16:00:05+00:00| seen| https://t.me/GithubRedTeam/85414 2026-05-22 19:00:10+00:00| seen| Telegram/GxW7z8duNlVdfiWWsv41lYfs7S7xkZAHymlGuRAZQODzxg...

CVE-2026-45250

creationtimestamp| type| source ---|---|--- 2026-05-21 05:00:04+00:00| seen| https://t.me/GithubRedTeam/85149 2026-05-21 07:00:13+00:00| seen| Telegram/0oVkH4V3C9Cndp9LVxg4I8W2m2s-mbtiL-m94vGYIMA5C-Q 2026-05-21 09:00:04+00:00| seen| Telegram/vpOabQVvb76izlIWt2pzp7PU5zl-D7jeeGQcHuuxEyFlkWM...

Luban-2040-v2

🛡️ Luban 2040 v2 Advanced Reconnaissance & Vulnerability...

shadow-pentest

🖤 Shadow Pentest Framework v1.0 Automated CVE Discovery & E...

GHSA-C4J6-FC7J-M34R

creationtimestamp| type| source ---|---|--- 2026-05-13 06:02:34+00:00| seen| https://t.me/GithubRedTeam/84034 2026-05-13 09:00:04+00:00| seen| Telegram/6gD9pQtVCgeRlU-Eqvw6JM83wq5C4Rc0rf2uF-yzttPU 2026-05-15 00:16:17+00:00| seen| https://gist.github.com/hahwul/e82a1e91f75872e43287743d4a15d035...

Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems

Agent skills extend LLM agents with reusable instructions, tool interfaces, and executable code, and users increasingly install third-party skills from marketplaces, repositories, and community channels. Because a skill exposes both executable behavior and context-setting documentation, its...

Your Purple Team Isn't Purple — It's Just Red and Blue in the Same Room

Defending a network at 2 am looks a lot like this: an analyst copy-pasting a hash from a PDF into a SIEM query. A red team script is being rewritten by hand so the blue team can use it. A patch waiting on a change-approval window that's longer than the exploitation window itself. Nobody in that...

CVE-2026-36980

creationtimestamp| type| source ---|---|--- 2026-05-10 21:00:04+00:00| seen| https://t.me/GithubRedTeam/83710 2026-05-10 23:00:14+00:00| seen| Telegram/4E6rSRxwI8rbj53U5V5E-Exh2Wmlv2Bw5SwE4GoCs4Wb5U 2026-05-11 03:00:06+00:00| seen| Telegram/mGI2CRHqQCjyvA6ju1XF5IWDLp0GZA5xrkAMw9kytXRmaE...

ViperForge

...