AI & security · Archive

AI & security

Dates are publishers’ publication dates, source update dates, or CISA catalog-added dates. First collected records when SecSIG first saw the entry.

• How to Create a Makeshift C2 with Claude Code as the Operator ↗ (opens in a new tab)

  G3tSyst3m’s Infosec Blog · Published 2026-06-26 · First collected 2026-10-24

• Auto reverse-engineering the Hyperliquid risk engine, with some agentic help ↗ (opens in a new tab)

  OtterSec · Published 2026-06-22 · First collected 2026-10-24

• SVD-2026-0614: OS Command Injection in the btool Configuration Helper in Splunk AI Toolkit ↗ (opens in a new tab)

  Splunk Security Announcements · Published 2026-06-17 · First collected 2026-10-24

• Captured Logs Reveal Hackers Using Claude and Codex to Breach Companies ↗ (opens in a new tab)

  OALABS Research · Published 2026-06-16 · First collected 2026-10-24

• Agentic AI Security is moving fast. Here’s where to start. ↗ (opens in a new tab)

  Confidential Computing Consortium · Published 2026-06-11 · First collected 2026-10-24

• Reflections of CDDC 2026 and my thoughts on AI in CTFs ↗ (opens in a new tab)

  Elma · Published 2026-06-11 · First collected 2026-10-24

• On the cyber-security implications of current LLMs ↗ (opens in a new tab)

  CERT.at news · Published 2026-06-01 · First collected 2026-10-24

• An AI audit of FreeBSD ↗ (opens in a new tab)

  Calif · Published 2026-05-28 · First collected 2026-10-24

• Securing AI systems without overconfidence or fear – Part 2: Attack surfaces and the checkpoint flow ↗ (opens in a new tab)

  NVISO Labs · Published 2026-05-22 · First collected 2026-10-24

• AI-FI: Reproducing adb to root on Google's TV Streamer using Claude in less than 15 minutes ↗ (opens in a new tab)

  Raelize - Embedded Device Security Testing, Consultancy & Training · Published 2026-05-19 · First collected 2026-10-24

• Benchmarking LLMs for malware triage and static unpacking with Malcat ↗ (opens in a new tab)

  MALCAT · Published 2026-05-17 · First collected 2026-10-24

• AI Vulnerability Research and the Fuzzer Era Déjà Vu: Why the Numbers Are Only Half the Story ↗ (opens in a new tab)

  VoidSec · Published 2026-05-12 · First collected 2026-10-24

• RCEliteLLM – LiteLLM 1.83.14: Chaining an Environment Variable Leak with Jinja2 SSTI for Remote Code Execution ↗ (opens in a new tab)

  McCaulay · Published 2026-05-11 · First collected 2026-10-24

• AI Security Architecture: The Key to Verifiable AI | Uptycs ↗ (opens in a new tab)

  Uptycs Blog · Published 2026-05-11 · First collected 2026-10-24

• Pentagon turns to AI targeting to help troops shoot drones ↗ (opens in a new tab)

  C4ISRNet · Published 2026-05-07 · First collected 2026-10-24

• OpenClaw and Claude in 2026, risks and retrospectives ↗ (opens in a new tab)

  Stormshield · Published 2026-05-07 · First collected 2026-10-24

• [Deprecated] Break LLM Workflows with Claude's Refusal Magic String ↗ (opens in a new tab)

  Hacking The Cloud · Published 2026-05-05 · First collected 2026-10-24

• pyghidra-mcp Meets Ghidra GUI: Drive Project-Wide RE with Local AI ↗ (opens in a new tab)

  clearbluejar · Published 2026-05-05 · First collected 2026-10-24

• Enabling privacy-preserving AI training on everyday devices ↗ (opens in a new tab)

  MIT News - Cybersecurity · Published 2026-04-29 · First collected 2026-10-24

• Can an AI Write a Working Exploit? ↗ (opens in a new tab)

  Lets Hack It · Published 2026-04-26 · First collected 2026-10-24

• Bissa Scanner Exposed: AI-Assisted Mass Exploitation and Credential Harvesting ↗ (opens in a new tab)

  The DFIR Report · Published 2026-04-22 · First collected 2026-10-24

• AI Made Code Cheap. Trust Did Not. ↗ (opens in a new tab)

  Theori BLOG · Published 2026-04-13 · First collected 2026-10-24

• Scanscope: Visualizing Port Scan Results Using Machine Learning Methods ↗ (opens in a new tab)

  SySS Tech Blog · Published 2026-04-09 · First collected 2026-10-24

• On LLMs and vulnerability research ↗ (opens in a new tab)

  devansh · Published 2026-04-06 · First collected 2026-10-24

• Observations on AI generated Remote DuckDB via HTTP with mTLS ↗ (opens in a new tab)

  DiabloHorn · Published 2026-03-22 · First collected 2026-10-24

• Are LLMs Capable Of Spatial Reasoning? A Small Experiment ↗ (opens in a new tab)

  Dino Hacks · Published 2026-03-19 · First collected 2026-10-24

• AI Exposure and CTEM: The Next Frontier of External Risk ↗ (opens in a new tab)

  RedHunt Labs · Published 2026-03-18 · First collected 2026-10-24

• OpenClaw at Work: Prompt Injection Risks ↗ (opens in a new tab)

  Promptfoo Blog · Published 2026-03-12 · First collected 2026-10-24

• Windows and macOS Malware Spreads via Fake “Claude Code” Google Ads ↗ (opens in a new tab)

  Bitdefender Labs · Published 2026-03-11 · First collected 2026-10-24

• Kali & LLM: Completely local with Ollama & 5ire ↗ (opens in a new tab)

  Kali Linux · Published 2026-03-10 · First collected 2026-10-24