CVE-2026-41713
A malicious user could craft input that is stored in conversation memory and later interpreted by the model in an unintended way.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.22%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
Description
A malicious user could craft input that is stored in conversation memory and later interpreted by the model in an unintended way. Applications using the affected advisor with user-controlled input may be susceptible to manipulation of model behavior across conversation turns.
- CVSS 3.1
- 8.2 HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:N
- EPSS
- 0.22% probability · 12th percentile
- Public exploits
- None in Exploit-DB
- CISA KEV
- Not listed
- Weakness
- CWE-1336
- Affected
- vmware/spring ai
- Source
- security@vmware.com
EPSS 0.2% since 26 October 2026; no change recorded yet. Points are recorded when the score first appears and whenever it moves by a percentage point or more.
References
- https://nvd.nist.gov/vuln-metrics/cvss/v3-calculator?vector=AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:N&version=3.1US Government Resource
- https://spring.io/security/cve-2026-41713Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA, exploits from Exploit-DB. Refreshed daily. Download this record as JSON.