CVE-2026-108592
mediumpriority · track · 31EPSS 0.003 · 24 %ileexploit · PoCEPSS · scored 2026-10-27
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.
cvss
Technical severity, 0–10. One row per scoring source.
base score 0–10 · higher = more severe · hover a vector to decode
ssvc
A stakeholder decision — act, attend, or track — from exploitation and impact.
weaknesses
The CWE weakness classes this flaw belongs to.
exploits (1)
Public proof-of-concept and weaponised exploit code.
affected products
Products and version ranges known to be affected.
No affected products recorded.
sources
Which sources assert this record, and when.
references (4) nvd
External citations — patches, advisories, analysis.
- https://github.com/SWE-agent/mini-swe-agent
- https://github.com/SWE-agent/mini-swe-agent/blob/v2.4.6/src/minisweagent/environments/extra/bubblewrap.py#L38-L103
- https://hackmd.io/@haind/minisweagent-bubblewrap-host-environment-leak
- https://www.vulncheck.com/advisories/mini-swe-agent-1.10.0-through-2.4.6-environment-exposure-via-bubblewrapenvironment
Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.
Free scan