PT-2025-6211

Name of the Vulnerable Software and Affected Versions: PandasAI versions 2.4.3 and earlier Description: PandasAI utilizes an interactive prompt function that is vulnerable to prompt injection, allowing the execution of arbitrary Python code. This can lead to Remote Code Execution RCE instead of t...

PandasAI 安全漏洞

PandasAI is a Python library that integrates generative AI functionality into pandas to make data frames conversational. A security vulnerability exists in PandasAI that stems from vulnerability to a prompt injection attack and running arbitrary Python code that could lead to Remote Code Executio...

PandasAI interactive prompt function can be exploited to run arbitrary Python code through prompt injection, which can lead to remote code execution (RCE)

Overview PandasAI, an open source project by SinaptikAI, has been found vulnerable to Prompt Injection attacks. An attacker with access to the chat prompt can craft malicious input that is interpreted as code, potentially achieving arbitrary code execution. In response, SinaptikAI has implemented...

CVE-2024-3098

A vulnerability was identified in the executils class of the llamaindex package, specifically within the safeeval function, allowing for prompt injection leading to arbitrary code execution. This issue arises due to insufficient validation of input, which can be exploited to bypass method...

CVE-2024-5565

The Vanna library uses a prompt function to present the user with visualized results, it is possible to alter the prompt using prompt injection and run arbitrary Python code instead of the intended visualization code. Specifically - allowing external input to the library’s “ask” method with...

CVE-2024-5826

In the latest version of vanna-ai/vanna, the vanna.ask function is vulnerable to remote code execution due to prompt injection. The root cause is the lack of a sandbox when executing LLM-generated code, allowing an attacker to manipulate the code executed by the exec function in...

CVE-2024-6331

stitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable to Local File Read LFI by Prompt Injection. The integration of Google Gimini 1.0 Pro with HarmBlockThreshold.BLOCKNONE for HarmCategory.HARMCATEGORYHATESPEECH and HarmCategory.HARMCATEGORYHARASSMENT i...

Invisible Prompt Injection: A Threat to AI Security

This article explains the invisible prompt injection, including how it works, an attack scenario, and how users can protect themselves...

LangChain < 0.2.5 SQLi through Prompt Injection

The version of LangChain installed on the remote host is prior to 0.2.5. It is, therefore, affected by a prompt injection vulnerability in the GraphCypherQAChain class which leads to SQL injection. This vulnerability permits unauthorized data manipulation, data exfiltration, denial of service DoS...

LangChain < 0.2.5 SQLi through Prompt Injection

The version of LangChain installed on the remote host is prior to 0.2.5. It is, therefore, affected by a vulnerability in the GraphCypherQAChain class which allows for SQL injection through prompt injection. This vulnerability can lead to unauthorized data manipulation, data exfiltration, denial ...

Imperva’s Wildest 2025 AppSec Predictions

Humans are spectacularly bad at predicting the future. Which is why, when someone appears to be able to do it on a regular basis, they are hailed as visionaries, luminaries and celebrated with cool names like Nostradamus and The Amazing Kreskin. Nostradamus made his fame on predictions about the...

New AI Jailbreak Method 'Bad Likert Judge' Boosts Attack Success Rates by Over 60%

Cybersecurity researchers have shed light on a new jailbreak technique that could be used to get past a large language model's LLM safety guardrails and produce potentially harmful or malicious responses. The multi-turn aka many-shot attack strategy has been codenamed Bad Likert Judge by Palo Alt...

Link Trap: GenAI Prompt Injection Attack

Prompt injection exploits vulnerabilities in generative AI to manipulate its behavior, even without extensive permissions. This attack can expose sensitive data, making awareness and preventive measures essential. Learn how it works and how to stay protected...

Link Trap: GenAI Prompt Injection Attack

Prompt injection exploits vulnerabilities in generative AI to manipulate its behavior, even without extensive permissions. This attack can expose sensitive data, making awareness and preventive measures essential. Learn how it works and how to stay protected...

Researchers Uncover Prompt Injection Vulnerabilities in DeepSeek and Claude AI

Details have emerged about a now-patched security flaw in the DeepSeek artificial intelligence AI chatbot that, if successfully exploited, could permit a bad actor to take control of a victim's account by means of a prompt injection attack. Security researcher Johann Rehberger, who has chronicled...

Announcing the Adaptive Prompt Injection Challenge (LLMail-Inject)

We are excited to introduce LLMail-Inject, a new challenge focused on evaluating state-of-the-art prompt injection defenses in a realistic simulated LLM-integrated email client. In this challenge, participants assume the role of an attacker who sends an email to a user. The user then queries the...

AI Under the Microscope—What’s Changed in the OWASP Top 10 for LLMs 2025

As AI continues to evolve, so do the threats and vulnerabilities that surround Large Language Models LLMs. The OWASP Top 10 for LLM Applications 2025 introduces critical updates that reflect the rapid changes in how these models are applied in real-world scenarios. While the list includes...

GHSA-5CPH-WVM9-45GJ Flowise OverrideConfig security vulnerability

Impact Flowise allows developers to inject configuration into the Chainflow during execution through the overrideConfig option. This is supported in both the frontend web integration and the backend Prediction API. This has a range of fundamental issues that are a major security vulnerability...

Flowise OverrideConfig security vulnerability

Impact Flowise allows developers to inject configuration into the Chainflow during execution through the overrideConfig option. This is supported in both the frontend web integration and the backend Prediction API. This has a range of fundamental issues that are a major security vulnerability...

PT-2024-40094 · Vm2 +1 · Vm2 +1

Name of the Vulnerable Software and Affected Versions: Flowise affected versions not specified Description: The issue allows developers to inject configuration into the Chainflow during execution through the overrideConfig option, which is supported in both the frontend web integration and the...