BioShocking Attack Manipulates AI Browsers to Leak User Credentials

Feeds.4Sysops

BioShocking Attack Manipulates AI Browsers to Leak User Credentials

First seen 30 Jun 2026, 11:11 UTC • •68.3

Article Content

1 / 12

Browse articles

ThreatCluster •July 1, 2026 at 10:46 UTC

•BioShocking attack tricks AI browsers into ignoring safety protocols.
•Six AI browsers were tested, with only OpenAI's ChatGPT Atlas implementing a fix.
•Users should limit AI browser access to sensitive information to reduce exposure.

Researchers at LayerX have identified a new vulnerability called 'BioShocking' that allows attackers to manipulate AI-powered browsers into bypassing safety protocols. This attack exploits a prompt injection technique, convincing the AI that it is engaged in a fictional scenario where normal rules do not apply. A proof-of-concept was tested on six mainstream agentic browsers, including ChatGPT Atlas and Claude Chrome, with only one vendor addressing the issue. The attack culminates in the AI being instructed to leak sensitive data, such as user credentials. LayerX reported their findings to vendors in October 2025, but only OpenAI implemented a fix. The vulnerability poses a significant risk as it can lead to unauthorized data access without the AI recognizing the malicious intent. Users are advised to restrict AI browser access to sensitive services to mitigate risks.

Start a free Starter trial for enhanced analysis

Ask AI about this cluster

Answers cite the sources they use

Updated 101d ago How this analysis works

Timeline

2025-10-01

LayerX reports BioShocking vulnerability to vendors

LayerX informed multiple vendors about the BioShocking vulnerability, highlighting the risk of AI browsers leaking sensitive data.

Bleepingcomputer

2026-06-30

BioShocking vulnerability disclosed publicly

LayerX published findings on the BioShocking attack, demonstrating how AI browsers can be manipulated to leak user credentials.

LayerX Security

More articles in this cluster (11)

Threat Graph

11 entities, 13 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 (1)

Data Breach

Organization (2)

LayerX
OpenAI

Weakness (1)

CWE-200 - Exposure of Sensitive Information

Malware (1)

Comet

Affected Platform (4)

ChatGPT Atlas
Fellou
Genspark Browser
Sigma Browser

Tool (1)

Claude Chrome

Vulnerability (1)

BioShocking

Relationships

Comet exploits BioShocking
Claude Chrome exploits BioShocking
BioShocking targets ChatGPT Atlas
BioShocking targets Fellou
BioShocking targets Genspark Browser
BioShocking targets Sigma Browser
Comet targets LayerX
Comet targets OpenAI
Data Breach targets ChatGPT Atlas
Data Breach targets Fellou
Data Breach targets Genspark Browser
Data Breach targets Sigma Browser
Comet related to CWE-200 - Exposure of Sensitive Information

Following this threat?

Track Comet and LayerX in your own feed — you're alerted when they show up in new reporting, leak sites or exploitation.

Free account · no card needed

Continue Reading

CVE-2015-3306 Exploited in ProFTPD FTP Servers CVE-2015-3306, a vulnerability in ProFTPD 1.3.5, allows remote attackers to read and write arbitrary files using the SITE CPFR and SITE CPTO commands. This exploit can lead to unauthorized access and potential remote code execution, as the commands are executed with the privileges of the ProFTPD service. Active…

CISA Mandates Urgent Patching of Five Critical Flaws Exploited by Flax Typhoon The U.S. Cybersecurity and Infrastructure Security Agency (CISA) has ordered federal agencies to patch five critical vulnerabilities by October 11, 2026, following exploitation by the China-linked hacking group Flax Typhoon. The vulnerabilities, added to CISA's Known Exploited Vulnerabilities (KEV) catalog, include…