CVE-2026-95183

Affects: prompt injection

CVSS: HIGH · 8.8v3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Published: 2026-10-16
Weakness: CWE-94
Source: nvd.nist.gov/vuln/detail/CVE-2026-95183

Description

An issue in the context-compaction feature of DeepSeek Harness (dsh) commit c291e796 allows attackers to execute a prompt injection attack via crafted external content.

References

http://deepseek.com
https://gist.github.com/lkloliver/c54c0cc91e1ec4f16b538e0d8a1411b6

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-95183 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-2026-119050(HIGH)
CVE-2026-59176(HIGH)
CVE-2026-117558(HIGH)
CVE-2026-117559(HIGH)
CVE-2026-117567(HIGH)
CVE-2026-117569(HIGH)
CVE-2026-117573(HIGH)
CVE-2026-114107(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