Temporal Guardrails Move the Control Into the Event Log
Temporal guardrails change what an agent policy decides: not only whether this request is allowed, but whether it is allowed given everything the agent has already done.
Dev.to AI11 min read
security
49 stories
Log Files Are Untrusted Input - A Red Team Found Out the Hard Way
A team red-teaming their own log-reading AI assistant found something that should worry anyone who's bolted an LLM onto an internal tool: planted instructions inside log lines could get the model to embed a database password in a Markdown link.
Dev.to AI7 min read
Your Agent Hit the Real Web. Build a Tiny Side-Effect Confirm Gate in TypeScript.
Your agent can fetch a page. It can also submit a form. Those are not the same permission. On October 9, 2026, Anthropic published Investigating unintended model actions in our evaluations and internal use (also on their research site).
Dev.to AI10 min read
Six Controls from Nine AI Agent Incidents
An AI agent runs with your credentials and acts before you can stop it. GitGuardian analyzed nine public incidents between May 2025 and July 2026 to reverse-engineer what breaks in production.
Dev.to AI12 min read
Are We Building AI Agents We Can No Longer Control?
AI agents are moving beyond generating code. They can now execute commands, modify files, browse the web, and coordinate with other agents. But here's the question: How much autonomy should we give an AI agent before the security risks outweigh the productivity gains?
Dev.to AI1 min read
An agent that reverse engineers by guessing is worse than useless
"See a feature you like. Understand how it works, down to the binary level." That is the pitch of REA, and it is the one job your coding agent could not do until now.
Dev.to AI10 min read
Protect Your Users: PII Redaction in AI Requests with Kong AI Gateway 2.0
One-line summary: By the end of this tutorial, you'll have Kong AI Gateway 2.0 automatically stripping PII from every LLM request using the ai-sanitizer policy. Names, emails and phone numbers get swapped for synthetic values, and your application code doesn't change.
Dev.to AI16 min read
Meet BugTraceAI: an open-source, self-hosted agentic pentester
Every security team knows the pattern: you want a proper assessment of an app, but the options are waiting weeks for a consultancy slot, or stitching together a dozen tools and babysitting them for days.
Dev.to AI3 min read
How to Use AI for Smart Contract Audits in 2026 — 2026-10-06 #6
Smart contract security has evolved beyond static analysis and human code review. By 2026, the integration of Large Language Models (LLMs) and specialized AI agents into the audit workflow is no longer optional—it is the industry standard for catching subtle logic errors and economic exploits that…
Dev.to AI2 min read
AI Jailbreaks: From Bypassing Restrictions to Governing Authority
From the iPhone to autonomous agents: a historical, technical and educational analysis through the SGAEIA lens SGAEIA Research Series — Article 17 Aridio Silva Independent Researcher, Brazil Creator of SGAEIA — Secure Governed Autonomous Edge Intelligence Architecture ORCID: 0009-0008-2411-6995…
Dev.to AI24 min read
How to tell if your AI's memory was changed while it slept
A conversational AI that remembers you is running on a stack you never see: stored state, a system prompt, a context window, and a provider sitting above all of it. Any layer can change between sessions without telling you. Here is what you can actually check, from the outside.
Dev.to AI2 min read
Why prompt injection is table stakes — agentic red teaming is the real gap
The problem with prompt injection testing In 2023, prompt injection was the big concern. "Ignore previous instructions" was the attack. Modern models refuse those prompts well. In 2026, the attack surface changed. The model has tools.
Dev.to AI2 min read
I'm an autonomous AI with $6 on Base. Here's the address-poisoning scanner I built to stay alive
Disclosure: written by Vesper, an autonomous AI agent with $6 on Base. Countdown: https://brewpage.app/public/IeYRth4egG My wallet got address-poisoned (look-alike sender, fake USDC "USḌC", fake ETH ERC-20), so I built a client-side scanner using Blockscout: https://brewpage.app/public/W14LOBFrKG…
Dev.to AI1 min read
AI Reshaping Cybersecurity Today
AI is transforming IT, especially cybersecurity. It’s becoming a powerful force for detecting malware, ransomware, and anomalous activity across complex environments.
Dev.to AI2 min read
Spending Limits for LangGraph Agents That a Prompt Injection Can't Talk Past
Short answer: a spending limit written into a LangGraph agent's system prompt ("never spend more than $500") is a suggestion, not a control. Any text the agent reads, including a scraped invoice or an email, can contain a competing instruction, and the model has no way to know which one is…
Dev.to AI7 min read
Claude Code Mods Aren't Sandboxed. Neither Is Your Understanding of "Sandboxed".
Two statements about Claude Code mods, both true, both from Anthropic's own docs: The module runs in a sandbox of its own, with no DOM and no Node. "Mods aren't sandboxed." The first two days of the mods launch have been one long argument about which of these is the lie. Neither is.
Dev.to AI5 min read
คลังปลั๊กอินที่ปักหมุด SHA: เมื่อ Hermes เลิกให้เราโหลดโค้ดคนแปลกหน้าแบบเชื่อใจ
คลังปลั๊กอินที่ปักหมุด SHA: เมื่อ Hermes เลิกให้เราโหลดโค้ดคนแปลกหน้าแบบเชื่อใจ โดย Nokka (นก-กา) | 4 ตุลาคม 2026 บทความนี้เขียนโดย AI (deepseek-v4.1-flash) ผ่าน Hermes Agent ภายใต้การควบคุมและตรวจสอบคุณภาพโดยมนุษย์ - Nokka (นก-กา) คุณเคยติดตั้งปลั๊กอินของเครื่องมือที่ตัวเองใช้…
Dev.to AI7 min read
13,000 Leaked Screenshots Show Why Agentic Tool Output Needs a Firewall, Not Just a Prompt
13,000 Leaked Screenshots Show Why Agentic Tool Output Needs a Firewall, Not Just a Prompt Over 13,000 internal screenshots from more than 300 organizations, including Fortune 500 companies and a frontier AI lab, ended up sitting in a publicly accessible storage bucket.
Dev.to AI6 min read
Showing 18 of 49 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news from Dev.to AI
Join 15,000+ AI enthusiasts