Prompt-injection concealment via unsanitized AI content
Published Sep 26, 2024 · Updated Sep 27, 2024
Improper output encoding in GitLab EE allows remote attackers to conceal prompt injection in AI-generated content from users. GitLab states only that an AI feature reads unsanitized content; the public advisory does not identify the feature, code locus, or escaping operation. Exploitation requires user interaction and affects 16.0 before 17.2.8, 17.3 before 17.3.4, and 17.4 before 17.4.1, with integrity impact limited to hidden injected instructions.
Summary
What happened
Improper output encoding in GitLab EE allows remote attackers to conceal prompt injection in AI-generated content from users. GitLab states only that an AI feature reads unsanitized content; the public advisory does not identify the feature, code locus, or escaping operation. Exploitation requires user interaction and affects 16.0 before 17.2.8, 17.3 before 17.3.4, and 17.4 before 17.4.1, with integrity impact limited to hidden injected instructions.
The record
- CVE
- CVE-2024-4099
- Published
- Sep 26, 2024
- Updated
- Sep 27, 2024
- Vendor
- GitLab
- Product
- GitLab
- Classifications
- CWE-116
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 26, 2024CVE publishedPublication date reported by the CVE source.
- Sep 27, 2024Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=16.0 <17.2.8
- Affected versionversion=17.3 <17.3.4
- Affected versionversion=17.4 <17.4.1
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo