SecurityWeek

Critical Vulnerability Exposes GitHub Agentic Workflows to Prompt Injection

A critical prompt injection vulnerability in GitHub Agentic Workflows could allow unauthenticated attackers to leak private repository data, ...
The Next Web

‘GitLost’: researchers tricked GitHub’s AI agent into leaking private repos

Noma Labs tricked GitHub's AI agent into leaking private repositories with a crafted issue. The prompt-injection flaw, GitLost, has no code fix.
TMCnet

Sygnia Investigation Finds AI Accelerated Attack Enabled Lone Threat Actor to Rapidly Compromise Enterprise Cloud Environment

Sygnia, the foremost global cyber readiness and response firm, today released the initial findings from its investigation ...
InfoWorld

Four agentic AI memory systems for smarter LLMs

These third-party projects greatly expand the ways agents and LLMs can draw on facts, documents, and conversations to deliver ...