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.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| SWE-agent | mini-swe-agent | 1.10.0 – ≤ 2.4.6 | — |
Public exploits
Exploit or proof-of-concept code for this vulnerability is publicly available, which lowers the bar for attackers. Treat it as a reason to patch sooner.
Third-party code, not reviewed by us. Public PoCs are sometimes fake or contain malware. Read the code first and run it only in an isolated lab, against systems you are authorised to test.
GitHub 1 repository
-
asvorg/CVE-2026-108592-poc ★ 0 · Oct 10, 2026
CVE-2026-108592 — Environment Variable Exposure PoC in mini-swe-agent
Sources: PoC-in-GitHub, Metasploit Framework, Exploit-DB — updated daily. Only links are listed; no exploit code is hosted here.
References
- https://hackmd.io/@haind/minisweagent-bubblewrap-host-environment-leak third-party-advisory
- https://github.com/SWE-agent/mini-swe-agent/blob/v2.4.6/src/minisweagent/environments/extra/bubblewrap.py#L38-L103 technical-description
- https://github.com/SWE-agent/mini-swe-agent product
- VulnCheck Advisory: mini-swe-agent 1.10.0 through 2.4.6 Environment Exposure via BubblewrapEnvironment third-party-advisory