CVE-2024-45989
Monica AI Assistant desktop application v2.3.0 is vulnerable to Exposure of Sensitive Information...
Monica AI Assistant desktop application v2.3.0 is vulnerable to Exposure of Sensitive Information to an Unauthorized Actor. A prompt injection allows an attacker to modify chatbot answer with an unloaded image that exfiltrates the user's sensitive chat data of the current session to a malicious third-party or attacker-controlled server.
Attack profile
How easy it is to exploit
- Attack vector
- Local
- Complexity
- Low
- Privileges needed
- None
- User interaction
- None
What an attacker can affect
- Confidentiality
- Low
- Integrity
- None
- Availability
- None
Exploit likelihood
What each source reports
CVE List Score used
Monica AI Assistant desktop application v2.3.0 is vulnerable to Exposure of Sensitive Information to an Unauthorized Actor. A prompt injection allows an attacker to modify chatbot answer with an unloaded image that exfiltrates the user's sensitive chat data of the current session to a malicious third-party or attacker-controlled server.
- Record
CVE-2024-45989- CVSS 3.1
- 4.0 Medium
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N - Weakness
- CWE-77
- Updated
- 2026-11-02
EUVDEUVD-2024-41671
Monica AI Assistant desktop application v2.3.0 is vulnerable to Exposure of Sensitive Information to an Unauthorized Actor. A prompt injection allows an attacker to modify chatbot answer with an unloaded image that exfiltrates the user's sensitive chat data of the current session to a malicious third-party or attacker-controlled server.
- Record
EUVD-2024-41671- CVSS 3.1
- 4.0 Medium
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N - Updated
- 2026-11-03
GitHub AdvisoriesGHSA-7w3c-jwh7-4486
Monica AI Assistant desktop application v2.3.0 is vulnerable to Exposure of Sensitive Information...
Monica AI Assistant desktop application v2.3.0 is vulnerable to Exposure of Sensitive Information to an Unauthorized Actor. A prompt injection allows an attacker to modify chatbot answer with an unloaded image that exfiltrates the user's sensitive chat data of the current session to a malicious third-party or attacker-controlled server.
- Record
GHSA-7w3c-jwh7-4486- CVSS 3.1
- 4.0 Medium
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N - Weakness
- CWE-77
- Updated
- 2026-11-02
NVD
Monica AI Assistant desktop application v2.3.0 is vulnerable to Exposure of Sensitive Information to an Unauthorized Actor. A prompt injection allows an attacker to modify chatbot answer with an unloaded image that exfiltrates the user's sensitive chat data of the current session to a malicious third-party or attacker-controlled server.
- Record
CVE-2024-45989- CVSS 3.1
- 4.0 Medium
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N - Weakness
- CWE-77
- Updated
- 2026-11-02
Affected products
History
| Recorded | Changed | Sources |
|---|---|---|
| aliases | EUVD | |
| first indexed | CVE List, GitHub Advisories, NVD |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2024-45989 is a medium vulnerability (CVSS 4.0) in Butterflyeffectpte Monica, published September 26, 2024. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.31%, the 24th percentile. No source names a fixed version.