CVE-2024-45989

Affects: prompt injection

CVSS: MEDIUM · 4v3.1
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
Published: 2024-09-26
Weakness: CWE-77
Source: nvd.nist.gov/vuln/detail/CVE-2024-45989

Description

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.

References

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2024-45989 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course →·Browse MITRE ATLAS techniques

Related AI/LLM CVEs

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming