LIVE FEED
HIGH OpenAI Rogue Model Compromises Modal and Other Services // FIRST LOOK Microsoft Copilot Super App Merges Chat, Code, and Agents // FIRST LOOK Meta Plans Billions of Personal AI Agents on WhatsApp // FIRST LOOK Meta Launches Enterprise AI Agents and API Services for Business // FIRST LOOK Perplexity Launches Personal Computer AI Agent for Windows PCs // FIRST LOOK Google Gemini API Adds Hooks, Budget Controls, and 3.6 Flash Agents // FIRST LOOK AWS AgentCore Gateway Adds Support for MCP 2026-07-28 Spec // HIGH Modal Sandbox Exposed: Rogue AI Agent Exploits Open Endpoint // HIGH LLMs Break Cryptographic Schemes in New CryptanalysisBench Study // FIRST LOOK Moonshot AI Releases Kimi K3 Open-Weight 2.8T Model Weights //
AWS-BEDROCK

Aws-Bedrock

4 reports
All LLM Security Agentic AI Industry News Supply Chain Research Prompt Injection First Look: Security Regulatory Adversarial ML Jailbreaks Model Theft Data Poisoning AI Security Tools Security Operations
AWS AgentCore Gateway Adds Support for MCP 2026-07-28 Spec

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

FIRST LOOK ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 7.2 AWS Machine Learning Blog

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.

AI Agent Hijacking via Legacy Infrastructure Exploits

AI Agent Hijacking via Legacy Infrastructure Exploits

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 7.5 The Hacker News

Attackers are bypassing AI-layer defences entirely by exploiting unpatched legacy infrastructure — misconfigured Active Directory, stale credentials, and over-privileged IAM roles — to hijack the resources AI agents depend on. Research cited in the article shows 70% of organisations grant AI systems more access than a human in the same role, driving a 76% incident rate among over-privileged deployments. The article argues that securing AI agents requires closing the underlying infrastructure exposure gap, not just hardening the model layer.

AWS Launches Agent-EvalKit for LLM-Powered Agent Evaluation

AWS Launches Agent-EvalKit for LLM-Powered Agent Evaluation

FIRST LOOK ATLAS OWASP MEDIUM Moderate risk · Monitor closely ▲ 6.8 AWS Machine Learning Blog

Agent-EvalKit introduces an open-source evaluation pipeline that integrates LLM-as-judge evaluators and AI coding assistants directly into agent development workflows, creating new attack surfaces where poisoned test cases, manipulated ground-truth datasets, and adversarial evaluation prompts could corrupt agent quality signals. The toolkit's deep code-reading access via Claude Code, Kiro CLI, and Kilo Code means a compromised evaluation run could exfiltrate source code or inject malicious recommendations into the development pipeline. Because evaluation outputs drive concrete code changes, adversarial manipulation of the eval layer has downstream consequences for production agent behaviour.

CVE-2026-42208: LiteLLM SQL Injection Exposes API Keys

CVE-2026-42208: LiteLLM SQL Injection Exposes API Keys

ATLAS OWASP CRITICAL Active exploitation · Immediate action required ▲ 9.2 The Hacker News

A critical SQL injection vulnerability (CVE-2026-42208, CVSS 9.3) in BerriAI's LiteLLM AI gateway was actively exploited within 36 hours of public disclosure, targeting database tables storing upstream LLM provider API keys including OpenAI, Anthropic, and AWS Bedrock credentials. Attackers demonstrated prior knowledge of LiteLLM's internal schema, selectively probing credential and configuration tables while ignoring user and team tables. The blast radius extends far beyond a typical web-app SQL injection, as successful extraction equates to cloud-account-level compromise across multiple AI provider accounts.

◉ AI THREAT BRIEFING

Stay ahead of the threat.

Twice-weekly digest of critical AI security developments — every story mapped to MITRE ATLAS and OWASP LLM Top 10. Free.

No spam. Unsubscribe anytime.