Skip to content

~ / IRONHACKERS

Red Team & AI Security_

News, writeups, technical posts and more.

Featured

Annual landscape

AI Security 2025 — annual dossier

ai-security · 30 min

AI Security 2025 — annual dossier

The year the three fronts went operational at the same time: agents in real production (Operator GA, Project Vend, MCP in clients), regulation with binding deadlines (DORA, Art. 5, GPAI) and AI at visible scale on both offence (XBOW #1 on HackerOne) and defence (AIxCC, Security Copilot Agents). Annual reference with a catalogue of releases, papers, incidents and cross-links to the year's technical writeups.

· Manuel López Pérez

Read full report →
Showing report 1 of 3

Latest Posts

View all posts »

Explore the most recent technical articles, tutorials, and vulnerability analyses published by the community.

Bulletin — May 2026

news · 13 min

Bulletin — May 2026

The Digital Omnibus reaches a provisional deal on 7 May: Annex III moves to December 2027. Spain approves its AI governance bill on 26 May. Pwn2Own Berlin pays out $1.3M for 47 zero-days, with Codex and Claude Code on the menu. Patch Tuesday ships with no zero-days for the first time since June 2024. OpenAI launches Daybreak and Anthropic moves Mythos toward GA. Verizon DBIR 2026 crowns vulnerability exploitation as the number-one vector. GitHub loses 3,800 internal repos to a poisoned VS Code extension.

· Manuel López Pérez

Agentic red team — from PentestGPT (2023) to XBOW #1 on HackerOne (2025)

ai-security · 13 min

Agentic red team — from PentestGPT (2023) to XBOW #1 on HackerOne (2025)

Three years of red team with LLMs. PentestGPT (Aalto/NTU paper, Aug 2023, USENIX 2024) opens the academic category; HackerGPT and WhiteRabbitNeo build the commercial side; XBOW (July 2025) reaches #1 globally on HackerOne with 1,060 reported vulns. Reproducible PoC with PentestGPT v2 against HackTheBox.

· Manuel López Pérez

AI infrastructure: two years of incidents that confirm the category

ai-security · 17 min

AI infrastructure: two years of incidents that confirm the category

Pickle as a broken legacy format, inference servers as a new HTTP attack surface, AI gateways as a pivot into the infra, and ML frameworks running with research-project security. The 2024–2026 arc with the Wiz / Oligo / JFrog / Orca / Datadog milestones and the PoCs they left behind.

· Manuel López Pérez

Bulletin — April 2026

news · 13 min

Bulletin — April 2026

The Omnibus trilogue closes without agreement on 28 April, leaving the original AI Act deadline three months away. Patch Tuesday with 165 CVEs and an active SharePoint zero-day. Anthropic announces Claude Mythos + Project Glasswing — the first frontier model held behind a defensive wall. Pwn2Own Berlin collapses under oversubscription. M&S one year on. AESIA publishes guides 13 and 14.

· Manuel López Pérez

EU AI Act Annex III: three months from 2 August, with Brussels' Digital Omnibus in mid-air

compliance · 18 min

EU AI Act Annex III: three months from 2 August, with Brussels' Digital Omnibus in mid-air

The third step of Regulation (EU) 2024/1689 enters application on 2 August 2026: Annex III high-risk systems, FRIA, post-market monitoring, CE marking, EU register. The Commission's Digital Omnibus proposes pushing it to 2 December 2027, but the 28 April trilogue closes without agreement. What to have ready on 2 August if Brussels doesn't make it.

· Manuel López Pérez

Bulletin — March 2026

news · 17 min

Bulletin — March 2026

LiteLLM supply chain: TeamPCP compromised Trivy first to reach the PyPI credentials of the maintainer and ship litellm 1.82.7 / 1.82.8 with a 3-stage payload. nginx-ui MCPwn (CVE-2026-33032, CVSS 9.8) exploited in the wild. Patch Tuesday loud on AI: XBOW takes the month's CVSS 9.8. Mandiant M-Trends 2026 reports 22 seconds between initial access and ransomware. VMware Aria Operations in CISA KEV. NVIDIA GTC presents NemoClaw for agentic security. DORA first Register of Information with 31 March deadline.

· Manuel López Pérez