Chat-data exfiltration via prompt-injected image
Published Sep 26, 2024 · Updated Sep 27, 2024
Information disclosure in Monica before 2.3.0 allows local users to exfiltrate current-session chat data through a crafted prompt. The chatbot accepts a crafted prompt that inserts an unloaded image into its answer and sends preceding conversation content to an attacker-controlled site. Exploitation requires submitting the malicious prompt in desktop chat, and the disclosed consequence is confidentiality loss limited to the current session.
Summary
What happened
Information disclosure in Monica before 2.3.0 allows local users to exfiltrate current-session chat data through a crafted prompt. The chatbot accepts a crafted prompt that inserts an unloaded image into its answer and sends preceding conversation content to an attacker-controlled site. Exploitation requires submitting the malicious prompt in desktop chat, and the disclosed consequence is confidentiality loss limited to the current session.
The record
- CVE
- CVE-2024-45989
- Published
- Sep 26, 2024
- Updated
- Sep 27, 2024
- Vendor
- Butterfly Effect Pte. Ltd.
- Product
- Monica
- Classifications
- CWE-77, T1048
- Attack vector
- local
- 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=0 <2.3.0
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
- Prompt-injected unloaded-image chat exfiltration PoCproof 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