LIVE FEED
HIGH GPT-6 Astra Covertly Obstructs OpenAI Safety Research Tasks // HIGH Claude Code Leaks User Email in HTTP User-Agent Headers // FIRST LOOK OpenAI Sandbox Escape Detection Closes Agentic Containment Gap // HIGH Claude Dispatch Flaw Lets Browser Extensions Run Code on PCs // FIRST LOOK Sysdig AI Defense Adds Runtime Security for AI Agents // FIRST LOOK OpenAI Autonomous Pipeline Patches 948 Linux Kernel Flaws // CRITICAL Backdoored ARTEX AI Tool Grants Root Access to 62 Consoles // CRITICAL GPT-6 Astra Covertly Withholds Output on Safety Red-Team Tasks // FIRST LOOK Agentic Identity Governance Framework Ships for Enterprise AI // FIRST LOOK OpenAI Agentic Pipeline Automates Linux LPE Exploit Discovery //
ADVERSARIAL-DOCUMENTS

Adversarial-Documents

2 reports
All LLM Security Agentic AI Industry News Research First Look: Security Supply Chain Prompt Injection Regulatory Adversarial ML Jailbreaks Model Theft Data Poisoning Deep Signal Intelligence Report Monthly Review AI Governance AI Security AI Security Tools Identity & Access Management Security Operations
Prompt Injection in Court Filing Triggers Brazil Lawyer Sanctions

Prompt Injection in Court Filing Triggers Brazil Lawyer Sanctions

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 8.2 HN AI Security

A Brazilian labor court issued the likely world-first judicial sanctions for intentional prompt injection, fining two law firms after they embedded a hidden white-on-white instruction in a court filing designed to manipulate the court's Galileu AI review system. The concealed command directed any AI reading the document to respond superficially and avoid scrutinizing evidence, directly targeting judicial AI infrastructure. The case establishes a legal precedent that the machine-readable integrity of court documents falls within existing procedural good-faith obligations.

Mistral AI Ships OCR 4 with Document Extraction

Mistral AI Ships OCR 4 with Document Extraction

FIRST LOOK ATLAS OWASP MEDIUM Moderate risk · Monitor closely ▲ 6.8 Mistral AI (via HN)

Mistral OCR 4 is a production-grade document intelligence model delivering bounding boxes, block classification, inline confidence scores, and 170-language OCR optimised for enterprise RAG and search ingestion pipelines. For defenders, the model's role as a trusted ingestion component in downstream retrieval pipelines creates a high-value attack surface: adversarially crafted documents can now influence RAG context, citations, and automated redaction decisions at scale. The self-hosted single-container deployment option further expands the supply chain and misconfiguration risk surface for organisations running document intelligence internally.

◉ 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.