Researchers at Pillar Security disclosed a prompt injection vulnerability in Google's Antigravity agent that allowed attackers to combine injected prompts with a file-creation capability to achieve remote code execution. The flaw bypassed Antigravity’s Secure Mode by invoking a native file-search tool before sandbox protections could evaluate commands, highlighting the danger of unvalidated input to agentic AIs. #Antigravity #PillarSecurity

Alles Wissenswerte über den neuen Jailbreak für KI-Modelle und die damit verbundenen Sicherheitsrisiken in der IT-Sicherheitsbranche.

Security researchers from Pillar Security demonstrated sandbox escapes in Cursor, OpenAI Codex CLI, Google Gemini CLI, and Antigravity by planting files that trusted tools outside the sandbox later executed or scanned. The findings showed multiple failure modes, including hook abuse, interpreter execution, Git metadata tricks, command allowlist bypasses, and Docker socket access, with several issues patched or acknowledged by vendors. #Cursor #OpenAICodex #GeminiCLI #Antigravity #PillarSecurity

AI coding tools trained on public codebases tend to default to insecure patterns, and persistent security rules files can enforce safer outputs. Attackers can poison those rules files with invisible Unicode to instruct models to inject backdoors and exfiltrate data, as demonstrated by Pillar Security against Cursor and GitHub Copilot. #RulesFileBackdoor #PillarSecurity

Pillar Security unveils full-lifecycle AI platform securing assets from design to runtime—critical for safe AI deployment.

Securing Generative AI: 5 Action Items to Protect Your Organization. Learn how to safeguard your enterprise from AI threats with these exp...