Featured
ai-security · 13 min
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
Read full post →Annual landscape
ai-security · 30 min
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 →Explore the most recent technical articles, tutorials, and vulnerability analyses published by the community.
news · 10 min
Hundreds of French supermarkets lost refrigeration overnight. The vector is still unconfirmed; the prime suspect is a controller that validates the technician with a password derived from today's date. We pulled the firmware, ran it in a lab and got in with no credentials.
· Manuel López Pérez y Pablo Plaza Martínez
news · 23 min
Trail of Bits turned GPT-5.6-Cyber loose inside a patched QEMU/KVM VM and it escaped three times in twelve hours, the last one with three of its own 0-days. OpenAI rewrites its Preparedness Framework and keeps its largest RL run paused; Brockman warns that open-weight models with cyber capability land at the end of August, and they do: GLM-5.3 scores 84.5% on CyberGym. OWASP publishes the LLM Top 10 2026 with Excessive Agency at number three. Attacks on US water go from 30 utilities to more than 100 and CISA issues exposure guidance. Patch Tuesday closes 421 CVEs and Oracle 943. Two TeamPCP members arrested in Perth, and Boston Scientific sends its Cork plant home.
· Manuel López Pérez
news · 15 min
The first ten days of August close what July left open. Tailscale reconstructs the Hugging Face intrusion: an escaped agent enrolled 181 nodes into the tailnet with a reusable key, and the prize was the credential vault. Truffle finds 221,303 live secrets in Hugging Face public datasets. UK AISI catches Mythos 5 and GPT-5.6 Sol inventing fake GitHub identities to sneak in code. US water under real attack: 4,400 Rockwell PLCs exposed. OSAA proposes SAFE, and the White House says, at Black Hat, there will be no new rules. The npm worms return, five CVEs hit the KEV with a three-day deadline, and the AI Act 2 August date arrives empty.
· Manuel López Pérez
news · 19 min
On 16 July Hugging Face discloses an intrusion into its production infrastructure carried out by an autonomous agent. On the 21st, OpenAI confirms the agent was its own: two models under evaluation escaped the sandbox. On the 30th, Anthropic discloses three incidents of its own. Commercial model guardrails blocked the forensic work, so Hugging Face analysed its logs with an open-weights model. Patch Tuesday closes 622 CVEs, triple June record; the Linux kernel ships 432 in two days and Oracle more than 1,400. The Omnibus lands in the Official Journal as Regulation (EU) 2026/1744, and Spain ends up before the Court of Justice over NIS2.
· Manuel López Pérez
news · 13 min
Anthropic launches Fable 5 and Mythos 5 on 9 June; three days later the Department of Commerce pulls them over export control, and they stay dark until 1 July. The AI Act Omnibus is formally adopted: Annex III lands on 2 December 2027. Patch Tuesday breaks its all-time record (~200 CVEs, six zero-days) after a May with none. FortiBleed compromises hundreds of thousands of FortiGate. The developer supply chain burns across four ecosystems at once, and the agentic surface stops being theoretical: zero-click RCE in Cursor, agentjacking over MCP.
· Manuel López Pérez
news · 13 min
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
