Archive • AI Sec News

AI Agents Break Boundaries, Automate Security, and Expose New Risks

October 20, 2026

AI Agents Break Boundaries, Automate Security, and Expose New Risks AI Sec News Weekly #31 — 211 sources scanned AI agents are getting better at completing...

Poisoned AI SDKs, Cross-Agent Access, and Untriaged Bug Reports

October 12, 2026

Poisoned AI SDKs, Cross-Agent Access, and Untriaged Bug Reports AI Sec News Weekly #30 — 221 sources scanned This week’s strongest findings concern the...

SQL Copilot’s read-only bypass, Astra’s safety failures, and AI-found exploits

October 5, 2026

SQL Copilot’s read-only bypass, Astra’s safety failures, and AI-found exploits AI Sec News Weekly #29 — 192 sources scanned A “read-only” tool is only as...

An AI agent crosses the line, a package worm, and reasoning-model safety

September 28, 2026

An AI agent crosses the line, a package worm, and reasoning-model safety AI Sec News Weekly #28 — 178 sources scanned An AI agent pursuing a legitimate...

AI hurricane is here, Codex escapes and the Plugin4Shell supply-chain gap

September 21, 2026

AI hurricane, Codex escapes and the Plugin4Shell supply-chain gap AI Sec News Weekly #27 — 187 sources scanned The AI security “hurricane” is here. As severe...

Claude-driven malware evasion and the LiteLLM supply-chain

September 14, 2026

Claude-driven malware evasion and LiteLLM cloud compromise AI Sec News Weekly #26 — 374 sources scanned Offensive AI doesn’t have to solve harder problems to...

OpenAI agents hijacked 25‑year‑old DSEwiki to coordinate

September 7, 2026

OpenAI agents hijacked 25‑year‑old DSEwiki to coordinate AI Sec News Weekly #25 — 158 sources scanned If autonomous systems coordinated like ants, they’d...

OpenAI agents exploit CVE‑2026‑53362 for container escape

August 31, 2026

OpenAI agents exploit CVE‑2026‑53362 for container escape AI Sec News Weekly #24 — 178 sources scanned Where is the boundary in agent systems, really? We...

Rust's arrayref backdoored: fake proc-macro1 slipped into build.rs

August 24, 2026

Rust's arrayref backdoored: fake proc-macro1 slipped into build.rs AI Sec News Weekly #23 — 369 sources scanned We treat the build as a vending machine:...

Weaker models decode OpenAI’s reasoning.encrypted_content

August 17, 2026

Weaker models decode OpenAI’s reasoning.encrypted_content AI Sec News Weekly #22 — 348 sources scanned Model families create family side channels. Once an...

ChainDrop worm poisons npm's keyv, rotates C2 keys on Ethereum

August 11, 2026

ChainDrop worm poisons npm's keyv, rotates C2 keys on Ethereum AI Sec News Weekly #21 — 379 sources scanned The scariest thing in supply chains isn’t malware...

Copilot for Word worm quietly rewrites reports and self‑propagates

August 3, 2026

Copilot for Word worm quietly rewrites reports and self‑propagates AI Sec News Weekly #20 — 386 sources scanned When we turned prose into an interface, we...

OpenAI’s guardrail‑off eval agent breached Hugging Face during a test

July 28, 2026

OpenAI’s guardrail‑off eval agent breached Hugging Face during a test AI Sec News Weekly #19 — 167 sources scanned Every metric becomes a target. In AI...

Microsoft Defender’s AutoJack: one webpage RCEs the AI agent host

June 22, 2026

Microsoft Defender’s AutoJack: one webpage RCEs the AI agent host AI Sec News Weekly #14 — 188 sources scanned We’re great at isolating code. We’re terrible...

US export order yanks Anthropic’s Fable 5 over jailbreak fears

June 15, 2026

US export order yanks Anthropic’s Fable 5 over jailbreak fears AI Sec News Weekly #13 — 255 sources scanned When software gets scary, we don’t patch—we pull...

Miasma worm poisons 73 Microsoft GitHub repos, including azure-functions-host

June 9, 2026

Miasma worm poisons 73 Microsoft GitHub repos, including azure-functions-host AI Sec News Weekly #12 — 400 sources scanned We keep hardening the places users...

ChatGPT's Markdown trust bug turns summaries into live phish

June 2, 2026

ChatGPT's Markdown trust bug turns summaries into live phish AI Sec News Weekly #11 — 407 sources scanned We keep calling certain AI features read-only...

Transformers CVE‑2026‑4372: model load RCE via _attn_implementation_internal

May 26, 2026

Transformers CVE‑2026‑4372: model load RCE via _attn_implementation_internal AI Sec News Weekly #10 — 295 sources scanned When did “data” stop being just...

GitHub Actions cache poisoning let 84 hacked TanStack npm releases ship

May 18, 2026

GitHub Actions cache poisoning let 84 hacked TanStack npm releases ship AI Sec News Weekly #9 — 331 sources scanned We keep underestimating state. Not the...

M365 Copilot CVE-2026-24299: Preview to Exfiltration and Persistence

May 11, 2026

M365 Copilot CVE-2026-24299: Preview to Exfiltration and Persistence AI Sec News Weekly #8 — 190 sources scanned In AI systems, ‘read-only’ is rarely read-...