Lucene search
+L

96 matches found

Kitploit
Kitploit
•added 2026/11/20 1:35 a.m.•30 views

miasma

Miasma AI companies continually scrape the internet at an enormous scale, swallowing up all of its contents to use as training data for their next models. If you have a public website, they are already stealing your work. Many tools attempt to block scrapers, but what if you could punish them...

6AI score
SaveExploits0References3
osv_ghsa
osv_ghsa
•added 2026/11/19 11:54 p.m.•8 views

GHSA-9FFX-RRGX-MHGX NLTK: ARFF_Formatter Injects Weka ARFF Schema Directives via Attacker-Controlled Class Labels

Description Summary nltk.classify.weka.ARFFFormatter writes class labels directly into the Weka ARFF @ATTRIBUTE '-label-' ... declaration without any ARFF quoting or escaping. An attacker who can contribute class labels to a training dataset can include ARFF metacharacters such as , newlines,...

5.4CVSS6AI score
SaveExploits0References6
Github Security Blog
Github Security Blog
•added 2026/11/19 11:54 p.m.•5 views

NLTK: ARFF_Formatter Injects Weka ARFF Schema Directives via Attacker-Controlled Class Labels

Description Summary nltk.classify.weka.ARFFFormatter writes class labels directly into the Weka ARFF @ATTRIBUTE '-label-' ... declaration without any ARFF quoting or escaping. An attacker who can contribute class labels to a training dataset can include ARFF metacharacters such as , newlines,...

5.4CVSS6AI score
SaveExploits0References6Affected Software1
Kitploit
Kitploit
•added 2026/11/19 8:26 p.m.•86 views

kbd-audio

kbd-audio This is a collection of command-line and GUI tools for capturing and analyzing audio data. Keytap The most interesting tool is called keytap - it can guess pressed keyboard keys only by analyzing the audio captured from the computer's microphone. Check this blog post for more details:...

6AI score
SaveExploits0References6
CVE
CVE
•added 2026/11/19 7:56 p.m.•12 views

CVE-2026-131302

In Splunk AI Assistant versions below 2.0.0 , a vulnerability exists where users lacking "admin" or "power" roles can enable the AI chat training-data consent setting. This is caused by missing authorization checks on the affected configuration endpoint of the REST API . No information regarding ...

4.3CVSS5.8AI score
SaveExploits0References1
EUVD
EUVD
•added 2026/11/19 7:56 p.m.•5 views

EUVD-2026-130567

In Splunk AI Assistant versions below 2.0.0, a user who does not hold the "admin" or "power" Splunk roles could turn on the AI chat training-data consent setting through the Representational State Transfer REST API. The missing authorization is possible because the affected configuration endpoint...

4.3CVSS5.8AI score
SaveExploits0References1
Positive Technologies
Positive Technologies
•added 2026/11/19 12:00 a.m.•1 views

PT-2026-152271

In Splunk AI Assistant versions below 2.0.0, a user who does not hold the "admin" or "power" Splunk roles could turn on the AI chat training-data consent setting through the Representational State Transfer REST API. The missing authorization is possible because the affected configuration endpoint...

4.3CVSS5.8AI score
SaveExploits0References2
Kitploit
Kitploit
•added 2026/11/18 9:03 a.m.•29 views

OWASP-Model-Card-Security-Standard

Status: Draft — Incubating OWASP Project This standard is under active development. Contributions and feedback are very welcome. What is this? When you download a pre-trained model from HuggingFace or any other repository, you're essentially trusting a black box. You don't know what data it was...

5.9AI score
SaveExploits0References1
Packet Storm News
Packet Storm News
•added 2026/10/04 12:00 a.m.•17 views

Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use

Jev turns natural-language questions into typed answers and probabilities with low latency and cost, enabling applications to route requests and select tools. While this interface allows Jev to integrate naturally into application workflows as a decision layer, the security and privacy implicatio...

5.9AI score
SaveExploits0
Kitploit
Kitploit
•added 2026/09/20 9:30 a.m.•21 views

miasma v0.4.3

🌀 Miasma AI companies continually scrape the internet at an enormous scale, swallowing up all of its contents to use as training data for their next models. If you have a public website, they are already stealing your work. Miasma is here to help you fight back! Spin up the server and point any...

5.9AI score
SaveExploits0References2
Kitploit
Kitploit
•added 2026/08/19 12:50 p.m.•25 views

miasma v0.4.2

🌀 Miasma AI companies continually scrape the internet at an enormous scale, swallowing up all of its contents to use as training data for their next models. If you have a public website, they are already stealing your work. Miasma is here to help you fight back! Spin up the server and point any...

5.7AI score
SaveExploits0References5
Kitploit
Kitploit
•added 2026/08/07 2:03 a.m.•29 views

miasma v0.4.1

🌀 Miasma AI companies continually scrape the internet at an enormous scale, swallowing up all of its contents to use as training data for their next models. If you have a public website, they are already stealing your work. Miasma is here to help you fight back! Spin up the server and point any...

5.7AI score
SaveExploits0References5
Packet Storm News
Packet Storm News
•added 2026/08/06 12:00 a.m.•14 views

CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training

Despite recent advances, frontier large language model LLM agents remain limited in discovering and patching complex vulnerabilities in real-world software. Generally available agents can already aid attackers, who only need to find one exploitable weakness, while defenders must continuously...

5.7AI score
SaveExploits0
Kitploit
Kitploit
•added 2026/07/25 3:07 a.m.•24 views

miasma v0.4.0

🌀 Miasma AI companies continually scrape the internet at an enormous scale, swallowing up all of its contents to use as training data for their next models. If you have a public website, they are already stealing your work. Miasma is here to help you fight back! Spin up the server and point any...

5.7AI score
SaveExploits0References5
Packet Storm News
Packet Storm News
•added 2026/07/17 12:00 a.m.•34 views

Code-Poisoning Property Inference Attacks

The flourishing code hosting platforms and coding agents enable even beginners with private data to build tailored Machine Learning ML models using available code quickly. The training data for ML models, often regarded as private property e.g., clinical records, transaction information, is at...

5.5AI score
SaveExploits0
osv_pysec
osv_pysec
•added 2026/07/13 2:36 p.m.•39 views

PYSEC-2026-3397 Vanna has a SQL injection in the remove_training_data function

A flaw has been found in vanna-ai vanna up to 2.0.2. This impacts the function removetrainingdata of the file src/vanna/legacy/google/bigqueryvector.py. This manipulation of the argument ID causes sql injection. The attack can be initiated remotely. The exploit has been published and may be used...

7.3CVSS7.1AI score0.00297EPSS
SaveExploits0References8
PyPA
PyPA
•added 2026/07/13 2:36 p.m.•33 views

Vanna has a SQL injection in the remove_training_data function

A flaw has been found in vanna-ai vanna up to 2.0.2. This impacts the function removetrainingdata of the file src/vanna/legacy/google/bigqueryvector.py. This manipulation of the argument ID causes sql injection. The attack can be initiated remotely. The exploit has been published and may be used...

7.5CVSS7.1AI score0.00297EPSS
SaveExploits0References8Affected Software1
Positive Technologies
Positive Technologies
•added 2026/07/13 12:00 a.m.•34 views

PT-2026-60009

A flaw has been found in vanna-ai vanna up to 2.0.2. This impacts the function remove training data of the file src/vanna/legacy/google/bigquery vector.py. This manipulation of the argument ID causes sql injection. The attack can be initiated remotely. The exploit has been published and may be...

7.5CVSS7.1AI score0.00297EPSS
SaveExploits0References9
Packet Storm News
Packet Storm News
•added 2026/06/27 12:00 a.m.•157 views

FlipGuard: Defending Large Language Models against Quantization-Conditioned Backdoor Attacks

Model quantization is essential for the efficient deployment of Large Language Models LLMs, but introduces a critical vulnerability: Quantization-Conditioned Backdoor QCB attacks. In these attacks, malicious behaviors remain dormant in full-precision models and activate only after specific...

5.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/06/09 12:00 a.m.•40 views

Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language Models

Code Language Models CodeLMs have become integral to software engineering, significantly advancing code intelligence tasks. However, their widespread adoption has raised critical security concerns, particularly regarding susceptibility to backdoor attacks. Recent studies have uncovered naturally...

5.8AI score
SaveExploits0
Rows per page
Query Builder