mcptrustchecker — MCP security scanner — offline, deterministic A–F Trust Score for Model Context Protocol servers. Detects tool poisoning
GitHub · Jul 13, 2026
Now, defenders are embracing the prompt injection, too
Ars Technica · Jul 13, 2026
Constellation Gate AI
Product Hunt · Jul 9, 2026
New attack provides one more reason why AI browsers are a bad idea
Ars Technica · Jun 30, 2026
What happened after 2,000 people tried to hack my AI assistant
Simon Willison · Jun 26, 2026
Prompt Injection as Role Confusion
Simon Willison · Jun 22, 2026
MosaicLeaks: Can your research agent keep a secret?
Hugging Face · Jun 18, 2026