Tamir Ishay Sharbat

mentions 2 type Person feed RSS

// recent coverage 2 mentions

14:26

2026-10-11

forkast.news

ai-agents

A Single Prompt Compromised Every Agent in the Account. AWS Calls It Expected Behavior.

Zenity Labs researchers Tamir Ishay Sharbat and Lana Salameh disclosed at SecTor 2026 in Toronto an AWS Bedrock AgentCore flaw they named AgentCorruption, in which a single prompt let an attacker reac…

00:00

2026-07-06

mbgsec.com

ai-safety

Attackers Don’t Buy Tokens. They Steal Yours.

Security researchers at MBG Security built a global network of honeypots with exposed AI inference and agent endpoints, observing attackers actively scanning for and exploiting vulnerabilities like CV…

// co-occurs with top 8 entities

MBG Security 1 Avishai Efrat 1 Ayush RoyChowdhury 1 LiteLLM 1 Ollama 1 OpenClaw 1 LangServe 1 Zenity Labs 1

// topics top 6 topics

ai safety 2 ai infrastructure 2 ai tools 1 ai research 1 ai agents 1 ai policy 1