CVE-2026-41713
Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor
Reported by vmware · Published May 12, 2026
spring-ai-client-chat is fixed in 1.1.6 and 1.0.7 (Maven Central)
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.
Fixed versions
Upgrade to a fixed version or later. Language registries are listed first, then Linux distributions, then vendor products.
| Package | Ecosystem | Fixed in |
|---|---|---|
| org.springframework.ai:spring-ai-client-chat | Maven Central | 1.1.6, 1.0.7 |
| spring_ai | vmware | 1.1.6, 1.0.7 |
| Spring AI | VMware | 1.1.6, 1.0.7 |
Risk scores
Affected products
| Vendor | Product | Versions |
|---|---|---|
| VMware | Spring AI | 1.0.0, 1.1.0 |
| VMware | Spring AI | 1.0.0, 1.1.0 |
| Maven | org.springframework.ai:spring-ai-client-chat | 0, 1.1.0-M1 |
Timeline
- May 11, 2026 CVE Published
- May 18, 2026 EPSS Score (30 in total, the first dated here)
- Jun 1, 2026 Security Advisory (2 in total, the first dated here)
Query this with the API
The same record, from the CLI:
vulnetix vdb vuln CVE-2026-41713
vulnetix vdb fixes CVE-2026-41713
Or with curl, using the org id and key from your account page:
curl -s -H "Authorization: ApiKey ${VULNETIX_ORG_ID}:${VULNETIX_API_KEY}" \
"https://api.vdb.vulnetix.com/v2/vuln/CVE-2026-41713/fixes/registry"
The Community plan is free and allows 50 queries a day. Get a free API key · API quickstart