AI Security Wire

Threat actors are embedding prompt injection payloads in third-party LLM plugins and data sources to hijack AI agent actions, exfiltrate data, and pivot within enterprise environments.

Research demonstrates that LLMs with large context windows can be reliably jailbroken by embedding hundreds of fictitious dialogues before the target request — a technique that scales with context length and bypasses standard safety training.

A practical framework for implementing prompt injection detection and containment at the API gateway layer — covering input sanitisation, context isolation, output filtering, and anomaly-based detection for production LLM deployments.

A critical deserialization vulnerability in a widely-deployed ML model serving framework allows unauthenticated remote code execution via crafted model files. Patch immediately — active exploitation observed in the wild.

A detailed post-mortem of a multi-stage intrusion in which threat actors used LLM-generated spear phishing, AI-assisted credential stuffing, and automated reconnaissance to compromise a wealth management firm — from initial access to detection.