SWE-agent

!warning Most of our current development effort is on mini-swe-agent, which has superseded SWE-agent. It matches the performance performance of SWE-agent, while being much simpler. See the FAQ for more details about the differences. Our general recommendation is to use mini-SWE-agent instead of...

mini-swe-agent 2.4.6 Environment Variable Exposure

mini-swe-agent versions 1.10.0 through 2.4.6 contain an environment variable exposure in BubblewrapEnvironment. The included proof of concept checks whether a harmless host environment marker is inherited by a sandboxed command...

Exploit for CVE-2026-108592

CVE-2026-108592 — Environment Variable Exposure PoC A proof o...

CVE-2026-108592

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...

CVE-2026-108592 mini-swe-agent 1.10.0 through 2.4.6 Environment Exposure via BubblewrapEnvironment

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...

CVE-2026-108592 mini-swe-agent 1.10.0 through 2.4.6 Environment Exposure via BubblewrapEnvironment

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...

CVE-2026-108592

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...

CVE-2026-108592 mini-swe-agent 1.10.0 through 2.4.6 Environment Exposure via BubblewrapEnvironment

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...

CVE-2026-108592

The mini-swe-agent software (versions 1.10.0 through 2.4.6 ) is vulnerable to an information exposure flaw within the BubblewrapEnvironment component. The root cause is that the underlying bwrap tool omits the --clearenv flag, causing sandboxed commands to inherit the host's environment variables...

EUVD-2026-96402

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...

PT-2026-109732

Name of the Vulnerable Software and Affected Versions mini-swe-agent versions 1.10.0 through 2.4.6 Description An information exposure issue exists in the BubblewrapEnvironment where the bwrap tool is executed without the --clearenv flag. This causes sandboxed commands to inherit the host...

CVE-2026-108592: Cleartext Storage of Sensitive Information in an Environment Variable

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...

SWE-agent mini-swe-agent encryption issue vulnerability

Versions SWE-agent mini-swe-agent from 1.10.0 through 2.4.6 contain an encryption vulnerability. This vulnerability stems from the omission of --clearenv in BubblewrapEnvironment, allowing sandbox commands to inherit the host environment. Attackers can exploit this by injecting prompts, enabling...