CVE-2025-66389

Affects: prompt injection

CVSS: HIGH · 7.5v3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Published: 2026-06-22
Weakness: CWE-552
Source: nvd.nist.gov/vuln/detail/CVE-2025-66389

Description

GitHub Copilot 1.372.0 allows filesystem access outside of a workspace folder (without user approval) via a file-handler URI parameter to fetch_webpage. Therefore, exfiltration could occur if there is indirect prompt injection.

References

https://blindcyber.com/2025/10/28/copilot-fun/
https://github.com/microsoft/vscode-copilot-chat/
https://github.com/microsoft/vscode/blob/03baef1008086ed4960042fa463e570072173bb5/src/vs/workbench/contrib/chat/electron-browser/tools/fetchPageTool.ts#L152

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2025-66389 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course →·Browse MITRE ATLAS techniques

Related AI/LLM CVEs

CVE-2026-10564(HIGH)
CVE-2026-55607(HIGH)
CVE-2026-48719(HIGH)
CVE-2024-58351(CRITICAL)
CVE-2026-12045(CRITICAL)
CVE-2026-22551(MEDIUM)
CVE-2026-44688(HIGH)
CVE-2026-46580(HIGH)

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming