AAndrey Lesnikov·5h agoFail-closed authorization for AI agent tool calls, and the audit record behind itPlatform teams already enforce fail-safe defaults for Kubernetes objects with RBAC and admission controllers such as OPA/Gatekeeper and Kyverno. My preprint, Fail-Closed Authorization for Tool-Using A7 min read·justrunme.hashnode.dev14XM
MMahmoud Daghash·7m agoHow to Protect Sensitive PDF Documents Before Sharing ThemA PDF can leak in four different ways, and each one has a different fix. A password stops a stranger from opening the file. It does nothing about a bank account number that should never have been in t5 min read·confileo-eng.hashnode.dev
Bbtf01·16m agoWhat auditing a Bitcoin 0.1.0 fork in 2026 turned upStatic analysis, three fuzzers, sanitizers and reproducible builds, and the four findings worth sharing.3 min read·bitflash.hashnode.dev
PPiyush Sahoo·19m agoWhat Is Number Masking? A Guide to Call MaskingHow a proxy number connects two people, how many numbers you need, and the telecom and privacy rules that apply16 min read·piyuzz.hashnode.dev
HHackerMe·36m agoWeb Hosting Ransomware: What Three Host Attacks Teach Site Owners About BackupsWeb hosting ransomware used to be a story about one customer's server. In the first half of November 2026 it became a story about the host itself. Three hosting providers, Beget and ESTT in Russia and5 min read·hackerme.hashnode.dev
SSunny Chokshi·1h agoLLM benchmark stimulus audit: 33 of 80 pairs not cleanSunny Chokshi. November 6, 2026. After my runs finished I did an LLM benchmark stimulus audit on my own matched pairs. Of the 80 pairs that have both a plain and an indirect form, 33 differ in more t5 min read·sunnychokshi.hashnode.dev
SSunny Chokshi·1h agoAdversarial code comments dataset for LLM reviewersSunny Chokshi. November 4, 2026. I wanted to know whether a comment can change what an LLM code reviewer says about the same code. So I built a small adversarial code comments dataset, CommentInject.3 min read·sunnychokshi.hashnode.dev
DDecillion team·1h agoA reader's idea for a second spend limit on AI agentsBudgets cap how much. Rate limits would cap how fast. Here's our thinking, and what we'd like to hear.3 min read·decillionai.hashnode.dev
HHackerMe·1h agoScammer website checker: how to tell if a site is legitPeople reach for a scammer website checker, or a legit website checker, when something feels off. It might be a shop they have never used, a payment page that arrived from a message, or a link they si10 min read·hackerme.hashnode.dev
EErik Nascimento·1h agoHow to keep Claude Code and Cursor from reading your .envCoding agents open .env files first when debugging. Permission rules, run-time injection and agent hooks that keep API keys out of their context.4 min read·safe8bit.hashnode.dev
