ThreatCluster

HackedGPT: Seven New Vulnerabilities in GPT-4o and GPT-5 Discovered

First seen 6 Nov 2025, 17:37 UTC • •38

Article Content

1 / 3

Browse articles

ThreatCluster •March 12, 2026 at 13:27 UTC

Seven new vulnerabilities have been identified in the GPT-4o and GPT-5 models, potentially allowing for zero-day exploits. These vulnerabilities affect users of the models and could lead to unauthorized access or manipulation of data. Security researchers are urging immediate attention to mitigate risks associated with these flaws.

Start a free Starter trial for enhanced analysis

Ask AI about this cluster

Answers cite the sources they use

Updated 227d ago How this analysis works

More articles in this cluster (2)

Threat Graph

4 entities, 2 inferred relationships (STIX 2.1).

The full threat graph for this incident is free in the 7-day Starter trial.

Create free account

No card · 30 seconds

See everything included

Technique (2)

Data Breach
Malware

Affected Platform (1)

GPT-4o

Tool (1)

Gpt-5

Relationships

Data Breach targets GPT-4o
Malware targets GPT-4o

Continue Reading

Critical BeyondTrust 9.3 Vulnerability Actively Exploited by Threat Actor A critical vulnerability (CVE-2026-102764) in BeyondTrust Remote Support has been discovered and is actively being exploited by the threat group ARMORY CASTLE, reportedly linked to China. The vulnerability, which has a CVSS score of 9.3, allows unauthenticated attackers to upload files and potentially compromise host…

Lazarus APT Launches Operation FlashHole Using AI and Post-Quantum Cryptography Kaspersky has identified a cyberespionage campaign, dubbed Operation FlashHole, attributed to the Lazarus APT group, active since July 2025. The campaign has targeted at least three organizations in South Korea's construction, software, and wire-communication sectors. Attack methods include spear-phishing emails…