Private issue exfiltration via prompt-injected markdown links
Published Feb 13, 2025 · Updated Feb 13, 2025
Prompt injection in affected GitLab EE releases allows remote authenticated users to exfiltrate private issue contents through Duo Chat. Duo Chat incorporates malicious instructions stored in a public issue into its LLM prompt and renders an attacker-directed Markdown link containing private data. Exploitation requires Duo Chat access, a victim who queries the poisoned issue, and a click on the generated link.
Summary
What happened
Prompt injection in affected GitLab EE releases allows remote authenticated users to exfiltrate private issue contents through Duo Chat. Duo Chat incorporates malicious instructions stored in a public issue into its LLM prompt and renders an attacker-directed Markdown link containing private data. Exploitation requires Duo Chat access, a victim who queries the poisoned issue, and a click on the generated link.
The record
- CVE
- CVE-2024-3303
- Published
- Feb 13, 2025
- Updated
- Feb 13, 2025
- Vendor
- GitLab
- Product
- GitLab
- Classifications
- CWE-1427, T1204.001
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Feb 13, 2025CVE publishedPublication date reported by the CVE source.
- Feb 13, 2025Record 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 <17.6.5
- Affected versionversion=17.7 <17.7.4
- Affected versionversion=17.8 <17.8.2
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
- HackerOne report 2418620 reproductionproof of concept · demonstrated
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