Improper Neutralization of Input Used for LLM Prompting in GitLab
13Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 6.4epss 0.4%
exploitation probability
0.4%top 69% of all CVEs
observed exploitation
nono source reports it
An issue was discovered in GitLab EE affecting all versions starting from 16.0 prior to 17.6.5, starting from 17.7 prior to 17.7.4, and starting from 17.8 prior to 17.8.2, which allows an attacker to exfiltrate contents of a private issue using prompt injection.
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:N
Affected products
GitLab · GitLab