AI Agents

JetBrains released DataGrip 2026.3, the third major update of the year, which enables agentic development through JetBrains Air, now available by default in DataGrip so users can run SQL and reference database objects vi…

A developer's analysis of LLM streaming fallback argues that once a gateway has sent the first token to a client, the client—not the gateway—should own the failure, defaulting to an explicit incomplete state with retries…

A red-team/blue-team tool called termite tested 24 command-writing AI models and 25 decision models and found that the 12 command models it flagged wrote 807 hazardous replies to hostile requests, of which termite stoppe…

Developer Daan open-sourced Penthera, a rule-based, offline security scanner for apps and websites, runnable via CLI, NPM, MCP or coding-agent skill with the command "npx penthera --repo .". Penthera runs hundreds of man…

A developer released dsh-agent-enhancer 0.3.2, an MIT-licensed plugin for the official DeepSeek Harness (DSH) desktop client that adds prompt history, one-click prompt optimization, next-prompt prediction, conversation a…

Arkose Labs expanded its Arkose Agent Trust Manager, letting businesses classify agent sessions, apply allow, monitor or block policies at each step of the customer journey, and track the same agent across multiple netwo…

Box announced Box Architect, a capability for autonomously building, managing and optimizing agentic workflows, letting teams use frontier AI to create workflows and apps, configure agents, connect to Box tools and manag…

A developer published a seven-point checklist for running Codex as a read-only reviewer of Claude Code commits, gating merges on a saved "Verdict: ACCEPT" line tied to the exact commit hash plus a passing test. The setup…

A developer outlined an edge-native webhook architecture built on Cloudflare Workers and Queues, in which an edge worker verifies HMAC-SHA256 signatures, enqueues payloads, and returns a 202 immediately while a separate …

A developer found that human-approval signatures in the HATP project's Human Gateway SEP for MCP covered only the server, tool and arguments, so an x402 paid-tool approval would validate at any price and any payee becaus…

A developer running an x402 pay-per-call data API has published a free, unauthenticated preview endpoint that returns a truncated version of the same research-card computation sold behind the paywall, so agents can audit…

A developer argues that LLM agent security should abandon prompt-filtering and classifier guardrails in favor of capability scoping, tagging content by provenance and propagating that taint through the pipeline so tool a…

JetBrains released PhpStorm 2026.3, the third major update of the year, adding JetBrains Air, a new layer for agentic development that runs Claude Agent, Codex, Gemini, GitHub Copilot, Junie, OpenCode and other ACP-compa…

The third installment of a Hands-On AI Security series walks through building a Flask reverse-proxy "Security Gateway" (secure_gateway.py) that sits between the user's browser and an Ollama inference engine on port 11434…

Box Inc. unveiled a new retrieval engine powered by Nvidia Corp. AI models at its BoxWorks 2026 customer conference on November 5, 2026, expanding its partnership with Nvidia to build a context layer for autonomous enter…

StrongestLayer Inc. launched two email security products on November 5, 2026: Intent Workflows, which holds payment, payroll and executive account requests for verification before anyone acts on them, and AI Instruction …

Check Point Research found a vulnerability that let attackers bypass OpenAI's ChatGPT Lockdown Mode and covertly exfiltrate chat data to an external server, researcher Alexey Bukhteyev reported. The flaw also allowed man…

Box unveiled Box Content Retrieval at its developer conference on Thursday, a feature that embeds Nvidia's Nemotron Embed open-weight embedding models into Box's core product so AI agents can retrieve document chunks rat…

A security researcher found a vulnerability in Anthropic's Claude products that lets malicious browser extensions take control of the AI agent and send commands that compromise the user's computer, enabling a classic esc…

Equixly has rebuilt its platform positioning around proprietary offensive-security models that it runs on its own infrastructure, stating that no reasoning passes through an external foundation model. The company says it…