/
attack_type:prompt_injection × latest_source_host:welivesecurity.com × limpar

Resultados

4 casos · pág. 1/1

welivesecurity.com · medium

UAC-0099 embeds decoy nuclear-weapon request in VBScript to trip LLM scanner guardrails ahead of MATCHBOIL loader (GuardBreaker)

ESET researchers observed the Russia-aligned group UAC-0099 embedding a decoy request for guidance on building a nuclear weapon in a comment inside a VBScript used in the early stages of an attack on a target in Ukraine. The comment was meant to trigger the safety guardrails of an LLM-powered code scanner so that it stops inspecting the f…

welivesecurity.com · low

Vibe-coded apps expose users to hardcoded secrets, weak access controls and prompt injection; Lovable-hosted app had 16 flaws

AI-assisted "vibe coding" is lowering the barrier to app development, but it is also producing apps with common security oversights that app marketplaces do not necessarily flag. The article cites a report that 84% of developers were using or planning to use AI tools, and a Lovable-hosted app in which a researcher found 16 vulnerabilities…

welivesecurity.com · medium

ESET: SMBs face AI agent supply chain and prompt injection risks alongside accelerated phishing, exploitation and ransomware

ESET analysis describes a two-pronged risk for small and mid-size businesses (SMBs): AI agents create new paths into business systems, while attackers use AI to add speed and scale to established threats. Between March and May 2026, ESET scanned almost 900,000 unique agent skills from popular repositories and found more than 25,000 suspic…