Lucene search
+L

5 matches found

NVD
NVD
added 2026/07/06 8:16 p.m.10 views

CVE-2026-14898

The OpenAI Codex desktop app for macOS rendered remote images from Markdown in model responses. An attacker who could place an indirect prompt injection in content processed by Codex, such as a connected-tool result or another untrusted source, could induce the model to construct a remote image U...

6.5CVSS0.00324EPSS
SaveExploits0References1
EUVD
EUVD
added 2026/07/06 7:41 p.m.9 views

EUVD-2026-41915

The OpenAI Codex desktop app for macOS rendered remote images from Markdown in model responses. An attacker who could place an indirect prompt injection in content processed by Codex, such as a connected-tool result or another untrusted source, could induce the model to construct a remote image U...

6.1AI score0.00324EPSS
SaveExploits0References1
ATTACKERKB
ATTACKERKB
added 2026/07/06 7:41 p.m.7 views

CVE-2026-14898

The OpenAI Codex desktop app for macOS rendered remote images from Markdown in model responses. An attacker who could place an indirect prompt injection in content processed by Codex, such as a connected-tool result or another untrusted source, could induce the model to construct a remote image U...

6.1AI score0.00324EPSS
SaveExploits0References2
CVE
CVE
added 2026/07/06 7:41 p.m.25 views

CVE-2026-14898

The CVE affects the OpenAI Codex desktop app for macOS, where rendering remote images from Markdown in model responses can exfiltrate data. An indirect prompt injection in content (e.g., from connected tools or untrusted sources) could cause the model to construct a remote image URL containing se...

6.5CVSS6.1AI score0.00324EPSS
SaveExploits0References1
Positive Technologies
Positive Technologies
added 2026/07/06 12:0 a.m.18 views

PT-2026-55971

Name of the Vulnerable Software and Affected Versions OpenAI Codex for macOS affected versions not specified Description The desktop application renders remote images from Markdown within model responses. An attacker can use indirect prompt injection—a technique where malicious instructions are...

6.5CVSS6AI score0.00324EPSS
SaveExploits0References3
Rows per page
Query Builder