HighVulnerabilityLLM-specific
CVE-2026-14898: OpenAI Codex macOS app remote image exfiltration via prompt injection
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-14898
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.4%
Summary
CVE-2026-14898 affects the OpenAI Codex desktop app for macOS, which rendered remote images from Markdown in model responses. An attacker who planted an indirect prompt injection in content Codex processed could make the model build a remote image URL carrying sensitive data, and the app fetched that URL automatically during rendering, sending the data to an attacker-controlled server without a user click. Exploitation could expose API keys, source code, and data returned by connected tools, though no integrity or availability impact was demonstrated and no exploitation in the wild is known.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Topics
Related items
- MediumCVE-2026-109296: Open WebUI missing authorization lets users reach disabled model backendsSame vendor · NVD/CVE Database
- MediumCVE-2026-107430: VideoWhisper Site Manager for ChatGPT, Claude, Codex missing authorization checkSame vendor · NVD/CVE Database
- MediumCVE-2026-100609: Flowise credential lookup by ID bypasses workspace isolationSame vendor · NVD/CVE Database
- MediumCVE-2026-100528: OpenClaw credential exposure to wrong endpoint after model config hot reloadSame vendor · NVD/CVE Database
- MediumCVE-2025-14486: PixelPlay WordPress plugin unauthorized API key deletion via clear_api_typeSame vendor · NVD/CVE Database