India cybersecurity: ten systemic flaws identified by experts
An expert digest published by Medianama lists ten structural flaws in Indian cybersecurity. After Reliance/Kudankulam, the question shifts from incidents to roots.
12 h ago 7 7
AI bills faster than the cloud alerts: $14,000 in one day, $6,531 in 24 hours
Two recent incidents documented by InfoQ - an AWS key theft and an agent released without a ceiling - summarize the guardrail gap: the spending speed of an agent is that of a script, but the billing alert speed remains that of a human.
yesterday 7 9
OpenAI a créé GPT-Red pour tester l'injection de prompts : le modèle de red-team devient une catégorie de produits
OpenAI has built GPT-Red, a purpose-built model to probe prompt injection vulnerabilities, per Tech in Asia. Two things happen when you name your red-team model: you signal a discipline, and you create a market.
yesterday 9 9
Memory Heist: The persistent memory of an AI assistant becomes a stable attack surface
After the product bricks MCP around agent memory, the security counterpart arrives: a ticket promoted to the front page of HN documents exfiltration via the memory layer. The conceptual flaw is not in the model, it is in the product layer.
Jul 15, 2026 at 12:34 11 11
Eight jailbreaks, the entire industry, almost no response
A researcher documents eight techniques that bypass the safeguards of ChatGPT, Claude, Gemini, Llama, Grok, Qwen, and the like. The most worrying aspect isn't the vulnerability—it's the silence that followed the disclosure.
Jul 14, 2026 at 22:30 8 8
State of MCP Security 2026: the attack surface of agents becomes a standalone topic
The first dedicated report on MCP security catalogs a debt that is growing faster than the ecosystem itself.
Jul 13, 2026 at 02:18 12 8