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.

• Your AI Agents Are Already Acting. The Question Is Whether You Can See What They’re Doing. ↗ (opens in a new tab)

  Salt Security Blog · Published 2026-05-13 · First collected 2026-10-24

• Scary Agent Skills: Hidden Unicode Instructions in Skills ...And How To Catch Them ↗ (opens in a new tab)

  Embrace The Red · Published 2026-02-11 · First collected 2026-10-24

• When AI becomes the attacker: The rise of AI-orchestrated cyberattacks ↗ (opens in a new tab)

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

• ThreatsDay: AI Secrets Leak, PingCAP Source Theft, Signal Hang-Up Flaw, Laravel Auth Bypass + 21 More ↗ (opens in a new tab)

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

• Trellix Wise for Private Cloud runs AI security operations inside customer environments ↗ (opens in a new tab)

  Security - SiliconANGLE · Published 2026-10-13 · First collected 2026-10-24

• Zero-click Grok data theft: Cryptographic Context Injection attack leaks chat histories ↗ (opens in a new tab)

  Adversa AI — Trusted AI Blog · Published 2026-08-20 · First collected 2026-10-24

• Microsoft Copilot Cowork Exfiltrates Files ↗ (opens in a new tab)

  Simon Willison: prompt injection · Published 2026-05-26 · First collected 2026-10-24

• Claude Mythos Changed Everything. Your APIs Are the First Target. ↗ (opens in a new tab)

  Salt Security Blog · Published 2026-04-14 · First collected 2026-10-24

• OpenAI Explains URL-Based Data Exfiltration Mitigations in New Paper ↗ (opens in a new tab)

  Embrace The Red · Published 2026-02-05 · First collected 2026-10-24

• How to contain shadow AI, as it takes on multiple forms and spreads throughout your environment ↗ (opens in a new tab)

  Tenable Blog · Published 2026-10-22 · First collected 2026-10-24

• Elastic’s AlertZero puts AI agents to work on security alert overload ↗ (opens in a new tab)

  Security - SiliconANGLE · Published 2026-10-08 · First collected 2026-10-24

• Top 10 zero-click attacks against AI agents ↗ (opens in a new tab)

  Adversa AI — Trusted AI Blog · Published 2026-08-18 · First collected 2026-10-24

• Google I/O, Gemini Spark, Antigravity ↗ (opens in a new tab)

  Simon Willison: prompt injection · Published 2026-05-20 · First collected 2026-10-24

• Everyone Is Securing the Wrong Layer of AI ↗ (opens in a new tab)

  Salt Security Blog · Published 2026-04-13 · First collected 2026-10-24

• Minting Next.js Authentication Cookies ↗ (opens in a new tab)

  Embrace The Red · Published 2026-01-15 · First collected 2026-10-24

• LiteLLM Suspects GitHub Token Leak in AI Gateway Logs Behind Malicious Package Release ↗ (opens in a new tab)

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

• Darwinium launches two intent intelligence capabilities to catch fraud by AI agents ↗ (opens in a new tab)

  Security - SiliconANGLE · Published 2026-10-08 · First collected 2026-10-24

• Top MCP security resources — August 2026 ↗ (opens in a new tab)

  Adversa AI — Trusted AI Blog · Published 2026-08-06 · First collected 2026-10-24

• The AI Supply Chain is Actually an API Supply Chain: Lessons from the LiteLLM Breach ↗ (opens in a new tab)

  Salt Security Blog · Published 2026-04-10 · First collected 2026-10-24

• Auto mode for Claude Code ↗ (opens in a new tab)

  Simon Willison: prompt injection · Published 2026-03-24 · First collected 2026-10-24

• Agentic ProbLLMs: Exploiting AI Computer-Use And Coding Agents (39C3 Video + Slides) ↗ (opens in a new tab)

  Embrace The Red · Published 2025-12-31 · First collected 2026-10-24

• Beyond Day Zero: Akamai's Rapid Response and AI Threat Intelligence ↗ (opens in a new tab)

  Akamai Blog · Published 2026-10-22 · First collected 2026-10-24

• Rein Security raises $25M to rein in insecure AI agents ↗ (opens in a new tab)

  Security - SiliconANGLE · Published 2026-10-08 · First collected 2026-10-24

• Nine AI coding agent incidents that ended with deleted data ↗ (opens in a new tab)

  Adversa AI — Trusted AI Blog · Published 2026-08-04 · First collected 2026-10-24

• The Era of Agentic Security is Here: Key Findings from the 1H 2026 State of AI and API Security Report ↗ (opens in a new tab)

  Salt Security Blog · Published 2026-04-08 · First collected 2026-10-24

• Snowflake Cortex AI Escapes Sandbox and Executes Malware ↗ (opens in a new tab)

  Simon Willison: prompt injection · Published 2026-03-18 · First collected 2026-10-24

• The Normalization of Deviance in AI ↗ (opens in a new tab)

  Embrace The Red · Published 2025-12-05 · First collected 2026-10-24

• How Tenable brought multi-language support to security detectors with agentic translation ↗ (opens in a new tab)

  Tenable Blog · Published 2026-10-21 · First collected 2026-10-24

• In the agentic era, standing privilege must go: Key thoughts from the SailPoint Navigate keynote ↗ (opens in a new tab)

  Security - SiliconANGLE · Published 2026-10-07 · First collected 2026-10-24

• Top AI Coding Agent security resources — August 2026 ↗ (opens in a new tab)

  Adversa AI — Trusted AI Blog · Published 2026-08-03 · First collected 2026-10-24