CVE-2023-32786

Affects: prompt injection, LangChain

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: 2023-10-20
Weakness: CWE-74
Source: nvd.nist.gov/vuln/detail/CVE-2023-32786

Description

In Langchain through 0.0.155, prompt injection allows an attacker to force the service to retrieve data from an arbitrary URL, essentially providing SSRF and potentially injecting content into downstream tasks.

References

https://gist.github.com/rharang/d265f46fc3161b31ac2e81db44d662e1
https://gist.github.com/rharang/d265f46fc3161b31ac2e81db44d662e1

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2023-32786 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-2025-66389(HIGH)
CVE-2026-55443(MEDIUM)
CVE-2024-58351(CRITICAL)
CVE-2026-12045(CRITICAL)
CVE-2026-22551(MEDIUM)

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