OpenAI: OpenAI Codex Desktop App for macOS Vulnerability Allows Attackers to Inject Indirect Prompt
By
Jeremy C
1d ago
Source
RankiteoOpenAI: OpenAI Codex Desktop App for macOS Vulnerability Allows Attackers to Inject Indirect Promptrankiteo.comNew OpenAI Codex macOS Vulnerability Enables Stealthy Data Exfiltration A recently disclosed vulnerability in the OpenAI Codex desktop application for macOS (tracked as CVE-2026-14898 ) allows attackers to exploit indirect prompt injection techniques to silently exfiltrate sensitive data. The flaw stems from the app’s handling of Markdown content in
You might also wanna read
GitHub: GitLost Vulnerability Tricks GitHub’s AI Agent into Leaking Private Repos
Rankiteo·1d ago
Microsoft: Public PoC Released for SharePoint Remote Code Execution Vulnerability
Rankiteo·1d ago
Dell: TrojPix Attack Uses Imperceptible Pixels to Steal Data From Air-Gapped Networks
Rankiteo·2d ago
fast-mcp-telegram and Telegram: Critical fast-mcp-telegram Vulnerability Lets Attackers Access Telegram Session Without Token
Rankiteo·2d ago
TriWest Healthcare Alliance: TriWest Data Breach Exposes Health Information
Rankiteo·1d ago
Markel Insurance, Markel Specialty, Markel Assurance, Markel Group Inc. and Markel International: Markel Corporation Data Breach Lawsuit Investigation
Rankiteo·1d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.