» Tag
prompt-injection
2 posts6–Jul 12, 2026
GitLost: A Public GitHub Issue Can Leak Private Repos
GitLost shows how a public GitHub issue and a one-word prefix bypass threat detection, leaking private repo contents via Agentic Workflows.
ai-agentsprompt-injectiongithubsecurityNew Attack Class: Agent Data Injection (ADI) in AI Agents
Researchers uncovered a new attack class that tricks AI agents via fake trusted metadata, exposing critical vulnerabilities in Claude, Codex, and Gemini CLI agents.
ai-securityprompt-injectionllm-agentscybersecurity