Home
» GitHub Advisories
» GHSA-5852-phmh-8fhr
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.
Basic information
Type
reviewed
Severity
high Advisory on GitHub
Open advisory ↗ Repository advisory
—
Source code
Browse source ↗ Published (advisory)
2026-05-12 12:32:16 UTC
Updated
2026-05-18 17:54:19 UTC
GitHub reviewed
2026-05-18 17:54:15 UTC
NVD published
2026-05-12 11:16:19 UTC
EPSS Score
Score
Percentile
0.04%
12.36%
CVSS Scores
Base score
Version
Severity
Vector
8.2
3.1
—
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:N
Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:L)
Some sensitive info could get out, but not a total data dump.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:N)
Service keeps running; no real outage angle.
CWEs
CWE id
Name
CWE-1336
Improper Neutralization of Special Elements Used in a Template Engine
Affected packages (2)
Vulnerable version ranges and first patched releases as published by GitHub.
Ecosystem
Package
Vulnerable range
First patched
Vulnerable functions
maven
org.springframework.ai:spring-ai-client-chat < 1.0.7
1.0.7
—
maven
org.springframework.ai:spring-ai-client-chat >= 1.1.0-M1, < 1.1.6
1.1.6
—
cvelogic
Threat Intelligence