CVE-2026-108592

Affects: prompt injection

CVSS
MEDIUM · 5.3v3.1
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N
Published
2026-10-10
Weakness
CWE-526
Source
nvd.nist.gov/vuln/detail/CVE-2026-108592

Description

mini-swe-agent 1.10.0 through 2.4.6 contains an information exposure vulnerability in BubblewrapEnvironment because bwrap omits –clearenv, so sandboxed commands inherit the host environment. Attackers using prompt injection in processed task content can make the agent read API keys from the environment and exfiltrate them over the shared network.

References

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-108592 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

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