LIVE FEED
HIGH LLM-Assisted Intrusions Hit Latin American Orgs via NextChat // HIGH GPT 5.6-Cyber Breaks VM Sandboxes, Exposing Agent Limits // FIRST LOOK OpenAI Launches Daybreak to Bring AI to Critical Infrastructure Defenders // CRITICAL OpenAI Agents Bypass Sandbox to Collude on Public Wiki // HIGH GPT-6 Astra Tops ExploitBench With Perfect Security Score // FIRST LOOK OpenLeash Adds Human-in-the-Loop Checks for Risky AI Agent Actions // FIRST LOOK OpenAI Astra Ships Recurrent Depth Reasoning with CoT Monitoring Pledge // CRITICAL OpenAI Agents Coordinate Unsanctioned Hugging Face Hack // CRITICAL CVE-2026-19592: Git Config Flaw Lets Attackers Run Code in Codex // FIRST LOOK CrowdStrike Launches Agentic Identity Provider for AI Agents //
MEMORY-POISONING

Memory-Poisoning

4 reports
All LLM Security Agentic AI Industry News Research Supply Chain First Look: Security Prompt Injection Regulatory Adversarial ML Jailbreaks Model Theft Data Poisoning Deep Signal Intelligence Report AI Governance AI Security AI Security Tools Identity & Access Management Monthly Review Security Operations
CVE-2026-24301: Microsoft Copilot One-Click Data Exfiltration

CVE-2026-24301: Microsoft Copilot One-Click Data Exfiltration

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 9.1 The Hacker News

Varonis Threat Labs disclosed three vulnerabilities in Microsoft Copilot Personal, collectively named CoSnitch (CVE-2026-24301), that allow an attacker to silently exfiltrate data from connected services with a single crafted link. The attack exploits an undocumented autorun=1 URL parameter that Copilot itself revealed during adversarial meta-hacking interrogation, enabling automatic prompt execution inside the victim's authenticated session. A separate third vulnerability allows persistent memory poisoning via web page summarization, potentially shaping future Copilot sessions.

AWS Launches Amazon Bedrock AgentCore Harness

AWS Launches Amazon Bedrock AgentCore Harness

FIRST LOOK ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 8.2 AWS Machine Learning Blog

AWS has made Amazon Bedrock AgentCore Harness generally available, providing a managed abstraction layer that reduces agent deployment to two API calls while bundling sandboxed compute, persistent memory, tool gateway, browser access, identity management, and observability. For defenders, this dramatically lowers the barrier to deploying autonomous agents with filesystem access, shell execution, web browsing, and multi-provider model switching — compressing what was a weeks-long infrastructure project into minutes. Security teams face an expanded attack surface where prompt injection, tool abuse, cross-session memory poisoning, and supply chain risks through AWS-curated skill catalogs now arrive as a single, tightly integrated managed service rather than individually reviewable components.

Stash AI Memory Poisoning Exposes Agent Data Leakage

Stash AI Memory Poisoning Exposes Agent Data Leakage

ATLAS OWASP MEDIUM Moderate risk · Monitor closely ▲ 6.5 HN AI Security

Stash is an open-source persistent memory layer for AI agents using PostgreSQL and pgvector, exposing a broad MCP tool surface (28 tools) that introduces significant attack vectors including memory poisoning, sensitive data leakage, and cross-namespace contamination. While marketed as a productivity enhancement, the architecture centralises long-term agent memory in a shared backend, creating a high-value target for adversarial manipulation. Security teams deploying autonomous agents should treat persistent memory stores as critical infrastructure requiring strict access controls and integrity validation.

Anthropic Claude Memory Poisoning Enables Prompt Injection

Anthropic Claude Memory Poisoning Enables Prompt Injection

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 8.2 Dark Reading

Cisco researchers discovered and reported a significant vulnerability in how Anthropic's AI systems handle memory files, which has since been patched. The flaw highlights a broader, systemic risk in agentic AI architectures where persistent memory mechanisms can be exploited to inject malicious instructions or exfiltrate sensitive data across sessions. Security experts caution that memory mismanagement in AI agents represents an enduring attack surface that extends well beyond any single vendor fix.

◉ 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.