Getting LLMs Drunk to Find Remote Linux Kernel OOB Writes (and More)

This blog post by Asim Viladi Oglu Manizada (April 28, 2026) describes how a custom “overengineered, self-orchestrating team of vulnerability-hunting agents” discovered 20+ CVEs over several months, including two remote unauthenticated out‑of‑bounds writes in the Linux kernel’s ksmbd (CVE‑2026‑31432, CVE‑2026‑31433). The author’s harness uses a “drunk” Qwen 3.5 27B derivative and GPT‑5.3‑Codex to find vulnerabilities. Key findings span Linux kernel (ksmbd), Docker, OpenSSL, CUPS (remote RCE to root chain), HAProxy, Caddy, Traefik, udisks, systemd‑machined, etcd, Squid, nginx, Firewalld, dnsmasq, CoreDNS, util‑linux, RabbitMQ, Asterisk, MySQL, and MariaDB. The post highlights three vulnerability categories: (1) “docs ↔ code mismatches” (e.g., Docker AuthZ bypass CVE‑2026‑34040, Caddy case‑sensitivity bypasses), (2) memory corruption bugs found via focused LLM analysis, and (3) compositional logic flaws (e.g., CUPS chain). The author concludes that LLMs can now find vulnerabilities autonomously, and that “getting them drunk” refers to tuning smaller models to be less constrained, enabling them to surface subtle bugs. 

https://heyitsas.im/posts/drinking-llms

Comments

Post a Comment

Popular posts from this blog

Prompt Engineering Demands Rigorous Evaluation

In the blog post “Prompt Engineering Requires Evaluation” on the Shostack + Associates website, the author argues that treating prompts for large language models (LLMs) merely as creative artefacts is insufficient. Engineering prompts properly demands structured evaluation frameworks — what the AI community calls “evals” — to test which prompt versions work better, with which models, and under which conditions. The post highlights that simply assuming a prompt is “good enough” creates risks when LLMs are integrated into production systems (e.g., for threat modeling). It advocates for measuring prompt performance, variation effects, and tool-chain dependencies (model, context, ancillary materials).  Ultimately the message is: prompt engineering should borrow disciplined practices from software engineering (versioning, testing, benchmarking) rather than relying on informal experimentation.  https://shostack.org/blog/prompt-enignieering-requires-evaluation/
Read more

SecObserve: Simplified Vulnerability and License Management for CI/CD Pipelines

 SecObserve is an open-source tool for managing vulnerabilities and licenses in software development and cloud environments. It integrates various vulnerability scanners into CI/CD pipelines using GitLab CI templates and GitHub Actions for streamlined setup. It offers a centralized dashboard for assessing and reporting vulnerabilities, with tools for filtering, sorting, and evaluating results. SecObserve supports automation and manual assessments to focus on resolving critical issues.  https://github.com/MaibornWolff/SecObserve/tree/dev
Read more

Top Post-Quantum Cryptography Solutions and Vendors Ranked for Quantum-Safe Security

The article reviews and ranks nine post-quantum cryptography providers whose products use NIST-approved quantum-resistant algorithms to safeguard systems as quantum computing advances, driven by impending federal mandates and increasing enterprise demand. It evaluates vendors on security strength, performance, ease of integration, deployment history, use-case support, and roadmap, highlighting offerings spanning blockchain protection, enterprise crypto-agility, hardware-level security, PKI lifecycle tools, quantum entropy key systems, and quantum key distribution to address the transition from classical cryptography to quantum-safe defenses.  https://aijourn.com/top-9-post-quantum-cryptography-solutions-compared-pqc-providers-ranked/
Read more