Remote code execution via unvalidated pickle cache
Published Aug 11, 2025 · Updated Aug 11, 2025
Deserialization in CodeFuse-AI ModelCache for LLM 0.2.0 and earlier allows remote attackers to execute arbitrary code via a poisoned cache. MapDataManager.init opens the configured cache file and passes its contents directly to pickle.load without validation or a restricted unpickler. An unauthenticated remote attacker who can poison the cache can run commands when the application initializes that cache, with the application's privileges.
Summary
What happened
Deserialization in CodeFuse-AI ModelCache for LLM 0.2.0 and earlier allows remote attackers to execute arbitrary code via a poisoned cache. MapDataManager.init opens the configured cache file and passes its contents directly to pickle.load without validation or a restricted unpickler. An unauthenticated remote attacker who can poison the cache can run commands when the application initializes that cache, with the application's privileges.
The record
- CVE
- CVE-2025-45146
- Published
- Aug 11, 2025
- Updated
- Aug 11, 2025
- Vendor
- Unknown vendor
- Product
- Unknown product
- Classifications
- CWE-502
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Aug 11, 2025CVE publishedPublication date reported by the CVE source.
- Aug 11, 2025Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
What conditions does exploitation require?
What is affected?
Affected products and versions are unavailable in this record.
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- Insecure deserialization in CodeFuse-AI ModelCache via Poisoned Cacheproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo