CVE-2026-107204
9.8 CRITICALpublic exploit availablePublished 2026-10-07 · Updated 2026-10-08
AI risk analysis
- Summary
- The vulnerability allows unauthenticated attackers to execute Python code via the /run_script endpoint, leading to remote code execution.
- Exploitability
- Exploitation is relatively straightforward as it requires posting scripts to the /run_script endpoint without authentication.
- Blast radius
- If exploited, attackers can execute arbitrary code as the LMCache process, potentially leading to full system compromise.
- Detection
- No reliable host or network indicator is derivable from the published description.
- Prioritized remediation
- Upgrade to LMCache 0.5.6 or later.
Analysis generated locally by qwen2.5:7b-instruct (no data left the box). AI-assisted — verify against primary sources before acting.
NVD description
LMCache through 0.5.5 contains an unauthenticated remote code execution vulnerability that allows remote attackers to execute Python code by posting scripts to the /run_script endpoint. Attackers can recover real builtins through the injected FastAPI app object, bypassing the guarded __import__, to import os and run operating system commands as the LMCache process.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Weaknesses
CWE-306
Public exploit & PoC references
- https://github.com/LMCache/LMCache
- https://github.com/LMCache/LMCache/blob/v0.5.5/lmcache/v1/internal_api_server/common/run_script_api.py#L54-L76
- https://github.com/LMCache/LMCache/blob/v0.5.5/lmcache/v1/multiprocess/http_apis/common_api.py#L41-L46
- https://github.com/LMCache/LMCache/issues/5510
- https://github.com/LMCache/LMCache/issues/5510
All references
- https://github.com/LMCache/LMCache
- https://github.com/LMCache/LMCache/blob/v0.5.5/lmcache/v1/internal_api_server/common/run_script_api.py#L54-L76
- https://github.com/LMCache/LMCache/blob/v0.5.5/lmcache/v1/multiprocess/http_apis/common_api.py#L41-L46
- https://github.com/LMCache/LMCache/issues/5510
- https://www.vulncheck.com/advisories/lmcache-through-0.5.5-unauthenticated-rce-via-run-script-endpoint
- https://github.com/LMCache/LMCache/issues/5510
Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.
Related CVEs
- HIGHCVE-2026-105115PoC
- CRITICALCVE-2026-13249
- HIGHCVE-2026-96455PoC
- CRITICALCVE-2023-54399
- CRITICALCVE-2023-54405PoC
- CRITICALCVE-2025-70518
- CRITICALCVE-2025-70521
- CRITICALCVE-2026-102427
Related by shared AI tags and CWE weakness class. Browse the full archive.