First Look: Security

Perplexity Launches Personal Computer AI Agent for Windows PCs

FIRST LOOK ATLAS OWASP HIGH ▲ 8.2 The Verge AI Jul 29, 2026

Perplexity has expanded its Personal Computer agentic tool to Windows, enabling a locally-run AI agent that can access files, Office 365 apps, and the web on behalf of enterprise users. This significantly expands the attack surface for defenders: a compromised or manipulated agent running with local system access can exfiltrate files, execute unauthorised actions, and pivot across cloud-connected Microsoft 365 services. Security teams should treat this as a high-privilege process requiring the same scrutiny as endpoint detection tools, with particular attention to prompt injection via locally-processed documents.

Google Gemini API Adds Hooks, Budget Controls, and 3.6 Flash Agents

FIRST LOOK ATLAS OWASP HIGH ▲ 7.2 Google DeepMind Blog Jul 29, 2026

Google has updated its Managed Agents in the Gemini API with Gemini 3.6 Flash as the new default model, environment hooks that allow interception of tool calls, budget controls, scheduled triggers, and free tier access. The introduction of environment hooks — which can block, lint, or audit tool calls inside the agent sandbox — creates a new interception layer that, if misconfigured or bypassed, could allow malicious tool calls to slip through undetected. Defenders deploying these agents must treat hooks as a critical trust boundary and scrutinise scheduled triggers and budget controls as potential abuse vectors for persistent, low-cost autonomous operations.

AWS AgentCore Gateway Adds Support for MCP 2026-07-28 Spec

FIRST LOOK ATLAS OWASP HIGH ▲ 7.2 AWS Machine Learning Blog Jul 29, 2026

AWS has released AgentCore Gateway with native support for the Model Context Protocol (MCP) 2026-07-28 specification, enabling standardised tool-use and context-sharing across agentic AI workloads on AWS infrastructure. For defenders, MCP-compliant gateways dramatically expand the inter-agent communication surface, introducing new vectors for prompt injection through tool responses, malicious server impersonation, and privilege escalation across agent boundaries. Security teams operating agentic pipelines on AWS must now treat MCP endpoints as high-value targets requiring the same scrutiny applied to API gateways and identity providers.

Moonshot AI Releases Kimi K3 Open-Weight 2.8T Model Weights

FIRST LOOK ATLAS OWASP MEDIUM ▲ 5.8 Simon Willison Jul 28, 2026

Moonshot AI has released the weights for Kimi K3, a 2.8 trillion parameter mixture-of-experts model (1.56TB), distributed under a restrictive 'open weight' licence that requires a separate commercial agreement for large MaaS operators. The public availability of weights at this scale materially lowers the barrier for adversarial fine-tuning, jailbreak research, and model-theft-adjacent supply chain attacks. Defenders deploying or downstream of K3 should assess licence compliance risk alongside the standard open-weight threat model.

Microsoft Launches MAI-Cyber-1-Flash Inside MDASH Platform

FIRST LOOK ATLAS OWASP HIGH ▲ 7.2 The Hacker News Jul 28, 2026

Microsoft has introduced MAI-Cyber-1-Flash, a cybersecurity-specific sparse mixture-of-experts model integrated into its MDASH vulnerability identification and remediation harness, claiming 95.95% on the CyberGym benchmark at 50% lower cost than its previous model mix. The system's agentic architecture — routing roughly 90% of tasks to the specialised smaller model and escalating the hardest 10% to GPT-5.4 — expands the attack surface for adversaries who can probe the routing logic, manipulate vulnerability-related inputs, or abuse the automated proof-of-concept generation pipeline. Defenders should treat MDASH as a high-value target given its privileged access to unpatched source code and its capacity to produce working exploits, and should audit access controls, output handling, and supply chain integrity before deployment.

AI Agent Security Shifts From Visibility to Enforcement Controls

FIRST LOOK ATLAS OWASP HIGH ▲ 7.8 The Hacker News Jul 27, 2026

Security practitioners are documenting a critical maturity gap in AI agent governance: organisations can now inventory deployed agents across SaaS, cloud, and developer environments, but lack enforcement mechanisms to constrain what those agents can actually do. The core risk is that AI agents operate without consistent identity, intent, ownership, or access boundaries, breaking every assumption that traditional IAM and least-privilege models rely on. Defenders must treat agent enforcement — not discovery — as the primary control objective, or risk a false sense of security from visibility tooling alone.

Google Gemma Tech Brings 28.9M LLM to ESP32 Microcontrollers

FIRST LOOK ATLAS OWASP HIGH ▲ 7.2 HN AI Security Jul 26, 2026

A developer has demonstrated a 28.9-million-parameter language model running entirely on an ESP32-S3 microcontroller costing approximately $8, leveraging Google's Gemma-derived Per-Layer Embeddings technique to fit the model into severely constrained hardware. This capability fundamentally shifts the threat model for embedded and IoT systems by enabling local, offline AI inference with no server-side visibility or logging. Defenders must now account for AI-driven logic executing on physically accessible, low-cost hardware that is difficult to monitor, patch, or audit at scale.

AWS Adds Bedrock Guardrails Best Practices for Code Generation

FIRST LOOK ATLAS OWASP MEDIUM ▲ 6.2 AWS Machine Learning Blog Jul 24, 2026

AWS has published guidance on applying Amazon Bedrock Guardrails to code generation workflows, detailing how to configure content filters, topic denials, and output controls for AI-assisted coding pipelines. For defenders, this surfaces the inverse risk: organisations that misconfigure or partially implement these guardrails expose code generation endpoints to prompt injection, malicious code output, and filter-evasion attacks. Security teams must treat guardrail configuration as a first-class security control, not a default-on safety net.

Anthropic Brings Voice Mode to Claude Opus and Sonnet Models

FIRST LOOK ATLAS OWASP HIGH ▲ 7.2 The Verge AI Jul 24, 2026

Anthropic has expanded Claude's voice mode to its more capable Opus and Sonnet models, with agentic integrations into productivity apps including Gmail, Slack, and Canva. This significantly widens the attack surface by combining a natural-language voice input channel with agentic action-taking capabilities across third-party platforms. Defenders must now account for voice-based prompt injection, cross-app lateral movement via conversational instruction, and the difficulty of auditing spoken-language interactions at scale.

Anthropic and OpenAI Open Vetted Cyber Programs for Offensive Researchers

FIRST LOOK ATLAS OWASP HIGH ▲ 7.2 TechCrunch AI Jul 24, 2026

Anthropic and OpenAI have introduced structured vetting programs — Anthropic's Cyber Verification Program and OpenAI's Trusted Access for Cyber — that grant approved offensive security researchers access to AI models with reduced cybersecurity guardrails. These programs create a two-tier access model where the boundary between legitimate researcher and malicious actor becomes a policy decision made by private companies, introducing new social-engineering and access-abuse vectors. Defenders must now account for the possibility that guardrail-reduced model access can be obtained through credential abuse, insider compromise, or vetting-process manipulation.

Agentic AI Disrupts Confidential Computing Security Boundaries

FIRST LOOK ATLAS OWASP HIGH ▲ 7.2 Dark Reading Jul 23, 2026

Agentic AI systems are introducing new security challenges to confidential computing environments, threatening the trust boundaries that Trusted Execution Environments (TEEs) and secure enclaves were designed to enforce. Defenders must contend with the fact that agents operating inside or alongside confidential compute environments can exfiltrate data, accept malicious instructions, or undermine attestation guarantees in ways that existing controls were not designed to catch. Security teams deploying AI pipelines adjacent to sensitive data vaults need to reassess their threat models to account for agentic autonomy as a new attack surface.

Yellow Teams Bring AI Offense and Defense Into One Security Function

FIRST LOOK ATLAS OWASP MEDIUM ▲ 5.5 Dark Reading Jul 14, 2026

Yellow teams are an emerging security practice in which engineers build both offensive and defensive AI tools to stress-test AI capabilities and expose vulnerabilities before adversaries do. This dual-role model compresses the feedback loop between red and blue functions, but it also concentrates privileged knowledge of exploitable AI weaknesses in a small group with broad system access. Defenders should assess the insider-risk and knowledge-management implications of consolidating offensive AI tooling within a single team.

Tracebit Ships AWS Context Bombing Defence Against AI Hacking Agents

FIRST LOOK ATLAS OWASP MEDIUM ▲ 7.8 Ars Technica Security Jul 14, 2026

Tracebit has demonstrated a defensive technique called 'context bombing' that plants forbidden prompt injections alongside cloud secrets in AWS environments, exploiting AI hacking agents' own safety guardrails to force them into refusal loops and halt attacks. Tested across five leading models and 152 runs, the technique reduced successful admin privilege escalation from 57% to 5% and complete compromise from 36% to 1%. While highly effective as a canary and disruption mechanism, the technique also introduces a novel countermeasure-evasion arms race: adversaries now have strong incentive to build agents with hardened or guardrail-bypassed reasoning loops specifically to defeat context bombs.

FriendMachine Launches Jacquard Lang for AI-Written Code Review

FIRST LOOK ATLAS OWASP MEDIUM ▲ 6.2 HN AI Security Jul 14, 2026

Jacquard is an open-source programming language purpose-built for a workflow where ML models generate code and humans review it, featuring a compact surface syntax, OCaml-based checker, and C-emitting compiler. This human-in-the-loop design introduces a new class of trust boundary risk: defenders must assess whether the review layer provides genuine semantic verification or creates a false sense of security that sophisticated AI-generated code can exploit. Supply chain and prompt-injection-adjacent risks emerge when the AI code-generation step itself becomes a target for adversarial manipulation, producing subtly malicious output that passes superficial human review.

OpenAI GPT-5.6 Sol Ships Faster Parallel Tool-Use for Agents

FIRST LOOK ATLAS OWASP MEDIUM ▲ 6.2 OpenAI (via HN) Jul 13, 2026

Ploy's migration guide documents GPT-5.6 Sol, OpenAI's new flagship model, which delivers significantly faster agentic task completion through aggressive parallel tool-call fanning — a behavioural departure from previous models. For defenders, this parallelism expands the blast radius of a compromised agent session, as more tool calls execute concurrently before any human or automated review can intercept them. Teams running production agents should reassess tool-call budgets, rate limits, and tracing assumptions that were calibrated to sequential incumbents like Claude Opus.

First Look: Security

Stay ahead of the threat.