Vulnerability details
CVE-2026-41713
VMware Spring AI
Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor
CVSS 3.1
8.2High
Official 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 scores
| Score | Version | Source | Vector |
|---|---|---|---|
| 8.2High | 3.1 | CVEProject cvelistV5 (CNA) (vmware) | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:N |
Affected products
| Vendor | Product | Versions | Source |
|---|---|---|---|
| VMware | Spring AI | 1.0.0 ≤ v < 1.0.7 | CVEProject cvelistV5 (CNA) |
| VMware | Spring AI | 1.1.0 ≤ v < 1.1.6 | CVEProject cvelistV5 (CNA) |
References and advisories
2
Alerts for this product's next CVEsFollow the product to get new vulnerabilities on Telegram.
Details
- Published
- 2026-05-12
- Last updated
- 2026-05-12
- State
- Published
- Assigner (CNA)
- vmware
Exploit prediction (EPSS)
0.21%
Probability of exploitation in 30 days
12.3%
Percentile (among all CVEs)
SSVC assessment (CISA)
- Automatable
- Yes
- Exploitation
- None
- Technical impact
- Partial
Weaknesses (CWE)
- CWE-1336Improper Neutralization of Special Elements Used in a Template Engine