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.

• Inside the Exchange Inspector: How Tenable uses OpenAI GPT cyber models to review open-source AI agents ↗ (opens in a new tab)

  Tenable Blog · Published 2026-10-08 · First collected 2026-10-24

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

  Adversa AI — Trusted AI Blog · Published 2026-07-06 · First collected 2026-10-24

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

  Simon Willison: prompt injection · Published 2025-12-10 · First collected 2026-10-24

• How to mitigate the risk from AI-generated apps built by your 'citizen coder' employees ↗ (opens in a new tab)

  Tenable Blog · Published 2026-10-06 · First collected 2026-10-24

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

  Adversa AI — Trusted AI Blog · Published 2026-07-02 · First collected 2026-10-24

• Claude 4.5 Opus' Soul Document ↗ (opens in a new tab)

  Simon Willison: prompt injection · Published 2025-12-02 · First collected 2026-10-24

• Beyond Identity: Governing the Agentic Enterprise ↗ (opens in a new tab)

  Akamai Blog · Published 2026-09-22 · First collected 2026-10-24

• GuardFall: a universal shell injection vulnerability in open-source AI agents ↗ (opens in a new tab)

  Adversa AI — Trusted AI Blog · Published 2026-06-30 · First collected 2026-10-24

• Google Antigravity Exfiltrates Data ↗ (opens in a new tab)

  Simon Willison: prompt injection · Published 2025-11-25 · First collected 2026-10-24

• What AI Can, Cannot, and Should Not Do ↗ (opens in a new tab)

  Akamai Blog · Published 2026-09-21 · First collected 2026-10-24

• OWASP ASI03: Identity & Privilege Abuse in AI Agents ↗ (opens in a new tab)

  Adversa AI — Trusted AI Blog · Published 2026-06-25 · First collected 2026-10-24

• Claude Opus 4.5, and why evaluating new LLMs is increasingly difficult ↗ (opens in a new tab)

  Simon Willison: prompt injection · Published 2025-11-24 · First collected 2026-10-24

• Solving the "Breaking the Prompt" DEF CON AI CTF with AI Red Teaming Agent ↗ (opens in a new tab)

  Adversa AI — Trusted AI Blog · Published 2026-06-23 · First collected 2026-10-24

• MCP Colors: Systematically deal with prompt injection risk ↗ (opens in a new tab)

  Simon Willison: prompt injection · Published 2025-11-04 · First collected 2026-10-24