CVE-2025-45146: ModelCache for LLM through v0.2.0 was discovered to contain an deserialization vulnerability via the component
CVE-2025-45146 is a critical-severity flaw (CVSS 9.8) affecting modelcache. Below: why it ranks where it does, which versions are affected, what to do, and the exact commands.
ModelCache for LLM through v0.2.0 was discovered to contain an deserialization vulnerability via the component /manager/data_manager.py. This vulnerability allows attackers to execute arbitrary code via supplying crafted data.
Why this priority
- Critical severity
- Public exploit reference
- Remotely exploitable, no login, no user action
A fixed release or distro patch exists.
Risk facts
| CVSS score | 9.8 (Critical) |
| Attack vector | Network (remote) |
| Attack complexity | Low |
| Privileges needed | None |
| User interaction | None |
| EPSS exploit chance | 0.8% (top 42%) |
| CISA exploited list | No |
| Weakness | CWE-502 |
| Published | 2025-08-11 |
| Last modified | 2026-06-17 |
Last updated 2026-06-17 · Sources: CVE Program, NVD, CISA KEV, EPSS and vendor advisories · How we score
Am I affected?
Timeline
- Published CVE record published
- Updated Record last modified
Scores and fixes here are computed automatically from those and other public sources. Confirm with the vendor advisory before changing production systems.
Quick answers
How do I fix CVE-2025-45146?
modelcache: upgrade to newer than 0.2.0. Exact commands for each OS are on this page.
Is CVE-2025-45146 being exploited?
CVE-2025-45146 is not on the CISA Known Exploited Vulnerabilities list at the time of the last update. Check again, as this can change.
What does CVE-2025-45146 affect?
CVE-2025-45146 affects modelcache. Severity is critical (CVSS 9.8). ModelCache for LLM through v0.2.0 was discovered to contain an deserialization vulnerability via the component /manager/data_manager.py. This vulnerability allows attackers to execute arbitrary code via supplying crafted data.
How urgent is CVE-2025-45146?
Priority 59/100. Critical severity; Public exploit reference; Remotely exploitable, no login, no user action