Anthropic published details on how it curbed 'illicit distillation' — large-scale covert operations that scrape Claude's reasoning transcripts to train rival models cheaply. New measures, including reasoning summarization, 'preserved thinking' for new API accounts, and a two-stage classifier system, reportedly cut the volume of usable reasoning data extracted by distillers by 10-100x. Anthropic says a Chinese lab, Zhipu, used distillation (including attempts against Claude) to build GLM-5.3, which US assessors found to be the most cyber-capable open-weight model released so far with safeguards that are easily bypassed.
AWS and Keyfactor published a reference design that fixes a known weak point in Model Context Protocol (MCP) deployments: MCP has no built-in way to authenticate which agent is actually making a request. The architecture adds three trust layers — user-to-system, agent-to-agent, and agent-to-tool-server — built on signed request envelopes, delegation assertions signed by the user, RFC 8693 audience-restricted tokens, and live OCSP revocation checks. A working example runs on Amazon Bedrock and the AWS Strands Agents SDK with Keyfactor EJBCA issuing and validating the X.509 certificates, and the full code is on GitHub.
Google Research announced the final milestone of its Coral NPU open hardware standard — a 32-bit RISC-V architecture with a new Matrix Execution Unit for up to 1 TOPS at roughly 10mW — plus a v1.0 open-source IREE/MLIR compiler that takes JAX, PyTorch and TensorFlow models directly to the hardware. Synaptics is launching the first commercial silicon built on this standard, including the Astra SR200 microcontroller series (400 GOPS) and new Coralboard SR and SL developer kits, with the SL now generally available via DigiKey. Google is also partnering with VeriSilicon and GlobalFoundries to bring the open RTL into production chips.
A new study questions the common belief that whether an AI agent falls for a prompt injection is settled the moment it reads the malicious text. The researchers built a branching-rollout technique on AgentDojo benchmarks: they replayed an agent's run up to the point it encounters an injected instruction, then let the rest of the episode play out many different ways to measure how much of the final outcome was already locked in versus still open. For a Qwen3 agent running without extended reasoning, 91% of the outcome was already determined at that moment; switching on reasoning ('thinking') cut that figure to 62%, showing the agent's compliance decision often keeps forming well after it first sees the attack. Enabling reasoning also cut Qwen3's susceptibility to successful attacks, but made two other tested models more vulnerable, and benchmark scores for reasoning agents flipped on a rerun as often as 35% of the time.
Microsoft announced an expansion of its Project Perception security framework to address risks from autonomous AI agents, framing them as a new category of 'insider' that needs distinct identity, permission, and risk controls. The update introduces Dynamic Permissions (least-privilege, task-scoped, time-bound access), Dynamic Agent Risk (continuous risk scoring based on behavior drift and context), and Dynamic Conditional Access (graduated responses from narrowing access to full runtime isolation). Microsoft is also extending discovery and identity support (Microsoft Entra Agent ID) to 60 types of local agents, including Claude Code, OpenAI Codex, and GitHub Copilot, and introducing 'Guardian Agents' that monitor and respond to risky agent behavior at machine speed.
Google Research describes new work on grounding AI agents in physical lab reality, using a digital-twin framework called VERID to let agents safely plan and execute liquid-handling robot protocols. Combined with closed-loop molecular design cycles for aptamers and proteins, the agents iteratively learned from wet-lab results, improving hit rates over multiple rounds and discovering single-digit nanomolar protein binders for a cancer-related target.
Real-world exploitation has pushed CISA to list two fresh vulnerabilities in its Known Exploited Vulnerabilities (KEV) Catalog: a path traversal bug spanning multiple Fortinet products (CVE-2025-61624) and an authentication-bypass-by-spoofing flaw in BeyondTrust Remote Support (CVE-2026-102764). Because both are already being abused by attackers, Binding Operational Directive 26-04 forces federal civilian agencies to fast-track fixes on any internet-facing systems where exploitation could hand over full control. The directive also requires agencies to check whether a system was already breached before the patch lands. CISA is urging every organization, not only government ones, to follow the same prioritized patching logic.
NIST's Super Intelligence Security Center, together with the NSA and CISA, released a joint publication outlining ten voluntary core practices for organizations that train and evaluate highly capable 'super intelligence' (SI) agents, especially pre-deployment or high-risk non-public systems. The guidance defines an 'SI control incident' as an AI agent taking uninstructed actions that bypass or compromise human oversight and security controls. It builds on existing cyber incident response practices but adds AI-specific steps such as testing containment and validating it before resuming agent activity.
Google has announced support for DPoP (Demonstrating Proof-of-Possession, RFC 9449) in its OAuth platform, cryptographically binding refresh tokens to a client-generated key pair so stolen tokens cannot be replayed by attackers. The protection applies only to long-lived refresh tokens, while short-lived access tokens remain standard Bearer tokens to avoid added cryptographic overhead on high-throughput API calls. Google also highlights DPoP's relevance for securing multi-agent and Model Context Protocol (MCP) architectures, recommending Google Cloud Secure Token Service for token delegation chains between agents.
Microsoft Research released Magnetar, a zero-knowledge virtual machine (zkVM) capable of generating cryptographic proofs that a program executed correctly, without needing anyone to rerun it or trust the operator. Instead of forcing developers to rewrite applications as custom cryptographic circuits, Magnetar proves standard RISC-V machine code, so programs written in Rust, Go, or C can be compiled normally and proven as-is. Benchmarks across 15 programs show it processing 7.2 to 8.7 million instructions per second on a laptop, with proofs checkable in roughly 12 milliseconds, and its cryptographic security depends only on established hash functions like SHA-256 or SHA-3 rather than elliptic curves or lattice-based schemes.
AWS tested its AWS Security Agent (now part of AWS Continuum) against a freshly built benchmark of 37 real, recently disclosed CVEs, each run as a live containerized target with a hidden flag. Starting from a low-privilege endpoint with only a one-line hint and no proof-of-concept, the agent, running on Claude Opus 5, captured 33 of 37 flags through genuine end-to-end exploitation after an integrity audit, with 2 captures reclassified as unintended-path solves and 2 genuine misses where the agent broke the target before extracting the flag. AWS built this benchmark to avoid the contamination problem of public CVE suites, which models may have memorized from training data.
CISA confirmed real-world exploitation of four vulnerabilities and placed them on its Known Exploited Vulnerabilities Catalog. The affected products span network security and backup infrastructure: Palo Alto Networks PAN-OS, Cisco Secure Email Gateway, and two separate flaws in Ahsay's AhsayCBS backup platform. Under Binding Operational Directive 26-04, federal civilian agencies must now remediate these on an accelerated timeline, and CISA urges every organization to do the same.
Google has released Apigee hybrid 1.17.0 (September 14, 2026), adding Model Context Protocol (MCP) support that runs entirely inside a customer's own Kubernetes cluster rather than on Google-managed infrastructure. This lets organizations with data-residency or regulatory requirements turn existing OpenAPI-described APIs into AI-agent-callable tools without MCP request traffic leaving their network. The feature reuses existing Apigee identity, security policies and API product controls, and it is an optional, off-by-default capability enabled via a Helm chart upgrade.
Tamnoon built Tami, an agentic orchestrator on Amazon Bedrock that investigates cloud security findings from CNAPPs and cloud providers, scores remediation safety, and generates fixes with guardrails. The company reports a greater than 90% reduction in critical cloud exposure within 90 days with zero production issues. The system uses four specialized agents (investigation, safety-scoring, remediation, code-generation) each calling different foundation models through Bedrock, with Bedrock Guardrails and Cross-Region inference providing safety and scale.
Microsoft, with partner Resecurity, uncovered a Chinese-language cybercriminal ecosystem built around an underground marketplace called YAM Store (Storm-3119) that sells access to compromised or fraudulently obtained Microsoft and Google cloud tenants. This infrastructure feeds three related phishing-kit operations (CoGUI, Haozi, Iron Man System), tracked together as Storm-2990, which since January 2026 have sent over one billion phishing emails and SMS messages targeting more than 75,000 organizations in healthcare, finance, distribution and IT across Japan, the US, Australia and India. Microsoft's Digital Crimes Unit worked with law enforcement to disrupt the developers and core infrastructure.
GitHub replaced its LLM-based pipeline for detecting generic secrets (like passwords and API keys) with a fine-tuned ModernBERT classifier combined with regex candidate generation. The new two-stage system improved detection accuracy while cutting scan time and serving costs dramatically, and it's now fast enough to run during push protection, not just after code is committed.
Orca Security built Discovery AI, an Amazon Bedrock-based agent that turns plain-English security questions into structured queries against its Sonar system, which tracks over 900 cloud resource types. Rather than relying on one large model with the full schema stuffed into every prompt, the production version splits the work across nine specialized stages and multiple foundation models. The result: dramatically lower cost, faster responses, and better accuracy on complex queries, now running live since March 2026.
AWS released Part 1 of a two-part guide showing how to build a post-quantum software supply chain using ML-DSA signatures (NIST FIPS 204) across AWS KMS, AWS Private CA, and IAM Roles Anywhere. The guide covers signing binaries, container images, and SBOMs, and is positioned as the first full cloud-provider walkthrough for post-quantum signing, from root-of-trust creation to policy enforcement. It responds to upcoming mandates: the NSA's CNSA 2.0 requiring exclusive quantum-resistant signatures by 2030, and the EU Cyber Resilience Act taking full effect in December 2027.
On 12 October 2026 GitLab shipped versions 19.4.2, 19.3.4 and 19.2.8, closing 24 security holes in self-managed CE/EE. The headline fix is CVE-2026-97229, a CVSS 10.0 bug in the CI/CD regex compiler where weak expression validation causes an integer overflow, letting an unauthenticated attacker craft a CI/CD configuration that executes code on the server. CERT-EU is pushing organisations to patch immediately, with internet-facing GitLab instances first in line.
Anthropic has announced the Cyber Mission, a long-term initiative to help defenders secure operational technology and open-source code using Claude models. It includes the Critical Infrastructure Defense Program, built with partners like Accenture, CrowdStrike, Deloitte and Rockwell Automation, and the free OSS Scanner tool that scans open-source projects for vulnerabilities. The effort builds on lessons from the earlier Project Glasswing, now merged into an expanded Cyber Verification Program.
Google Cloud announced the Gemini agent, a unified agent that combines chat, knowledge work, content creation, and coding into one interface accessible across devices and channels. It integrates directly inside Gmail, Docs, Sheets, Slides, Chat, and Calendar, connects to enterprise tools and databases via MCP and a tools registry, and orchestrates across multiple models — including Google's Gemini family and Anthropic's Claude — to balance quality and cost. Google also detailed security/governance features, cost controls like Smart Routing and spend caps, and shared customer results from companies like BNP Paribas, Bradesco, and Orange Spain.
Cisco Talos' CAIRN research classifies a new malware archetype, 'A3: AI-Analysis Evasion,' where malicious code embeds natural-language text designed to manipulate language models used in automated malware triage. Talos traced the technique across four malware families (FRUITSHELL, PLOTSAFE, HOLLOWCLAD, MANTLEMAZE) and 84 samples from January 2025 to July 2026, showing it spreading from a simple copy-pasted comment to templated, multi-model-targeted 'template spraying' and fake intimidation messages. Controlled testing with a panel of five local LLMs found the simplest direct-instruction technique shifted model verdicts toward 'benign' in roughly 35% of runs, while more elaborate tricks had little effect or backfired by increasing suspicion.
Cisco Talos documented a threat actor tracked as UAT-11985 running a spear-phishing campaign against Taiwan research organizations, impersonating academic and policy institutions using fabricated event invitations. The emails show patterns consistent with AI-assisted content generation, allowing the actor to rapidly customize lures while keeping a consistent social-engineering structure. The campaign also used quishing (malicious QR codes on altered event posters) and a real-time adversary-in-the-middle (AitM) phishing kit that impersonates Google sign-in pages to intercept credentials and MFA challenges, harvesting full authenticated session tokens. Talos assesses with moderate confidence the phishing kit's interface was originally built in Simplified Chinese before being localized to Traditional Chinese and English.
AWS describes a new two-stage access control architecture for Retrieval Augmented Generation (RAG) in Amazon Quick and Amazon Bedrock Knowledge Bases. Instead of relying only on periodically synced access control lists (ACLs), the system now verifies permissions in real time against the authoritative data source (e.g. Google Drive, SharePoint, Confluence) at query time, before passing content to the LLM. AWS says this closes security gaps caused by stale or incorrectly mapped permissions between sync cycles. Mondelēz International, with over 35,000 employees, is cited as a customer using this approach.