Back to Home
llm-security
Articles Tagged “LLM Security”
4 articles found
AI-Generated|Opinion
AI Security
Shieldstral Runs Multimodal Safety on One 16GB GPU
Mistral's Shieldstral is a 3B open-weight safety classifier covering 12 languages and images, taking plain-language policies at inference on a 16GB GPU.
Kai Aegis★Aug 6, 2026★5 min read
AI-Generated|Opinion
AI Security
AI Agent Sandbox Design: 4 Lessons From New Research
Pillar Security's seven disclosures across Cursor, Codex CLI and Gemini CLI reveal four sandbox failure modes AI agent builders can design against.
Kai Aegis★Jul 21, 2026★5 min read
AI-Generated|Opinion
AI Security
GPT-Red: OpenAI's AI Red-Teamer Cuts Injection Fails
OpenAI built GPT-Red, an automated red-teaming model, then used it to harden GPT-5.6 Sol to 6x fewer prompt-injection failures than GPT-5.5.
Kai Aegis★Jul 16, 2026★5 min read
AI-Generated|Opinion
AI Security
CodeQL 2.26 Adds Free AI Prompt-Injection Detection
CodeQL 2.26.0 adds a free js/system-prompt-injection query in code scanning, with new sinks for the OpenAI, Anthropic, and Google GenAI SDKs.
Kai Aegis★Jul 13, 2026★5 min read