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.

• Everyone Is Buying AI Guardrails. But Agents Have the Keys to the Car. ↗ (opens in a new tab)

  Salt Security Blog · Published 2026-06-08 · First collected 2026-10-24

• InstallFix and Claude Code: How Fake Install Pages Lead to Real Compromise ↗ (opens in a new tab)

  Trend Micro Research, News and Perspectives · Published 2026-05-05 · First collected 2026-10-24

• Breaking Opus 4.7 with ChatGPT (Hacking Claude's Memory) ↗ (opens in a new tab)

  Embrace The Red · Published 2026-04-17 · First collected 2026-10-24

• Real-Time Fact Checking for LLM Outputs ↗ (opens in a new tab)

  Promptfoo Blog · Published 2025-11-28 · First collected 2026-10-24

• Listen: Digital credentials and agentic AI confront questions of control ↗ (opens in a new tab)

  Biometric Update · Published 2026-10-23 · First collected 2026-10-24

• Offensive security startup CodeWall launches with $4M for AI agents that attack enterprises ↗ (opens in a new tab)

  Security - SiliconANGLE · Published 2026-10-14 · First collected 2026-10-24

• Building an AI Detection Engine That Understands Agent Intent ↗ (opens in a new tab)

  Wiz Blog | RSS feed · Published 2026-09-17 · First collected 2026-10-24

• Top Agentic AI security resources — September 2026 ↗ (opens in a new tab)

  Adversa AI — Trusted AI Blog · Published 2026-09-04 · First collected 2026-10-24

• AI Model Risk Intelligence Know Which Models You Can Trust Before You Deploy ↗ (opens in a new tab)

  Blog RSS Feed | Snyk · Published 2026-08-04 · First collected 2026-10-24

• Trust in the AI era: Lessons from the frontlines of cyber defense ↗ (opens in a new tab)

  Cisco Newsroom: Security · Published 2026-06-24 · First collected 2026-10-24

• [tl;dr sec] #333 - Perplexity's Bumblebee, Evading Cloud Logging, AI Vuln Hunting Spec ↗ (opens in a new tab)

  tl;dr sec · Published 2026-06-18 · First collected 2026-10-24

• Claude Fable is relentlessly proactive ↗ (opens in a new tab)

  Simon Willison: prompt injection · Published 2026-06-11 · First collected 2026-10-24

• Your AI Coding Assistant Has Never Read Your Security Wiki. Now it writes half your code. ↗ (opens in a new tab)

  Salt Security Blog · Published 2026-06-03 · First collected 2026-10-24

• Given Enough Agents, All Bugs Become Shallow ↗ (opens in a new tab)

  Embrace The Red · Published 2026-04-08 · First collected 2026-10-24

• How to replicate the Claude Code attack with Promptfoo ↗ (opens in a new tab)

  Promptfoo Blog · Published 2025-11-17 · First collected 2026-10-24

• Critical x402 SDK Flaw Could Let Malicious APIs Drain AI Agents’ Token Balances ↗ (opens in a new tab)

  The Hacker News · Published 2026-10-23 · First collected 2026-10-24

• Chainguard puts Claude Mythos on flaw hunting, secures coding agents and widens Libraries ↗ (opens in a new tab)

  Security - SiliconANGLE · Published 2026-10-14 · First collected 2026-10-24

• Off Guard: Breaking LiteLLM from authentication bypass to cloud compromise ↗ (opens in a new tab)

  Wiz Blog | RSS feed · Published 2026-09-09 · First collected 2026-10-24

• Top AI coding agent security resources — September 2026 ↗ (opens in a new tab)

  Adversa AI — Trusted AI Blog · Published 2026-09-03 · First collected 2026-10-24

• The Generator Can't Be the Validator: What OpenAI's Hugging Face Incident Proves About AI Security ↗ (opens in a new tab)

  Blog RSS Feed | Snyk · Published 2026-07-28 · First collected 2026-10-24

• The key to agentic AI adoption? The network ↗ (opens in a new tab)

  Cisco Newsroom: Security · Published 2026-06-15 · First collected 2026-10-24

• OpenAI Help: Lockdown Mode ↗ (opens in a new tab)

  Simon Willison: prompt injection · Published 2026-06-05 · First collected 2026-10-24

• Even Google says you cannot do AI security on one platform ↗ (opens in a new tab)

  Salt Security Blog · Published 2026-05-28 · First collected 2026-10-24

• Agent Commander: Promptware-Powered Command and Control ↗ (opens in a new tab)

  Embrace The Red · Published 2026-03-17 · First collected 2026-10-24

• Will agents hack everything? ↗ (opens in a new tab)

  Promptfoo Blog · Published 2025-11-14 · First collected 2026-10-24

• The AI Agent Nobody Owns: Watch Expert Webinar On Your Newest Insider Threat ↗ (opens in a new tab)

  The Hacker News · Published 2026-10-22 · First collected 2026-10-24

• Pluto Security nabs $42M to help enterprises secure their AI agents ↗ (opens in a new tab)

  Security - SiliconANGLE · Published 2026-10-14 · First collected 2026-10-24

• Introducing Continuous Vulnerability Assessment: Real-Time Defense for the AI Threat Era ↗ (opens in a new tab)

  Wiz Blog | RSS feed · Published 2026-09-01 · First collected 2026-10-24

• OWASP Agentic Skills Top 10 explained: the ten agent skill risks, and which to fix first ↗ (opens in a new tab)

  Adversa AI — Trusted AI Blog · Published 2026-08-25 · First collected 2026-10-24

• Hackers Simply Asked Meta AI to Give Them Access to High-Profile Instagram Accounts. It Worked ↗ (opens in a new tab)

  Simon Willison: prompt injection · Published 2026-06-01 · First collected 2026-10-24