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-2024-5565 Prompt Injection in "ask" API with visualization leads to RCE

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-2024-5565 Prompt Injection in "ask" API with visualization leads to RCE

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...

PT-2024-36568

Name of the Vulnerable Software and Affected Versions Vanna library affected versions not specified Description The Vanna library is affected by a remote code execution issue due to prompt injection. This allows an attacker to alter the prompt function used for visualized results and run arbitrar...

LLMs’ Data-Control Path Insecurity

Back in the 1960s, if you played a 2,600Hz tone into an AT&T pay phone, you could make calls without paying. A phone hacker named John Draper noticed that the plastic whistle that came free in a box of Captain Crunch cereal worked to make the right sound. That became his hacker name, and everyone...

GHSA-WVPX-G427-Q9WC llama-index-core Prompt Injection vulnerability leading to Arbitrary Code Execution

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-2024-3098

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-2024-3098 Prompt Injection leading to Arbitrary Code Execution in run-llama/llama_index

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-2024-3098 Prompt Injection leading to Arbitrary Code Execution in run-llama/llama_index

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-2024-3098 Prompt Injection leading to Arbitrary Code Execution in run-llama/llama_index

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...

PT-2024-23701

Name of the Vulnerable Software and Affected Versions llama index package affected versions not specified Description A vulnerability was identified in the exec utils class of the llama index package, specifically within the safe eval function, allowing for prompt injection leading to arbitrary...

LlamaIndex 代码注入漏洞

LlamaIndex is a data framework for an LLM application by the individual developer Jerry Liu. A code injection vulnerability exists in LlamaIndex that stems from insufficient input validation of the safeeval function in executils, which allows injection at the prompt, leading to arbitrary code...

A Taxonomy of Prompt Injection Attacks

Researchers ran a global prompt hacking competition, and have documented the results in a paper that both gives a lot of good examples and tries to organize a taxonomy of effective prompt injection strategies. It seems as if the most common successful strategy is the "compound instruction attack,...

New Image/Video Prompt Injection Attacks

Simon Willison has been playing with the video processing capabilities of the new Gemini Pro 1.5 model from Google, and its really impressive. Which means a lot of scary new video prompt injection attacks. And remember, given the current state of technology, prompt injection attacks are impossibl...

GitHub: Source Code and data exfiltration via Github Copilot

The vulnerability was caused by insecure output handling in the Copilot client interfaces. A prompt injection attack was able to result in data exfiltration. The vulnerability was addressed by only rendering images from trusted domains and adding interstitial modals to inform users about link...

Data Exfiltration Using Indirect Prompt Injection

Interesting attack on a LLM: In Writer, users can enter a ChatGPT-like session to edit or create their documents. In this chat session, the LLM can retrieve information from sources on the web to assist users in creation of their documents. We show that attackers can prepare websites that, when a...

GHSA-6H8P-4HX9-W66C Langchain Server-Side Request Forgery vulnerability

In Langchain before 0.0.329, prompt injection allows an attacker to force the service to retrieve data from an arbitrary URL, essentially providing SSRF and potentially injecting content into downstream tasks...

GHSA-8H5W-F6Q9-WG35 Langchain SQL Injection vulnerability

In Langchain before 0.0.247, prompt injection allows execution of arbitrary code against the SQL service provided by the chain...

CVE-2023-32786

In Langchain through 0.0.155, prompt injection allows an attacker to force the service to retrieve data from an arbitrary URL, essentially providing SSRF and potentially injecting content into downstream tasks...

CVE-2023-32786

In Langchain through 0.0.155, prompt injection allows an attacker to force the service to retrieve data from an arbitrary URL, essentially providing SSRF and potentially injecting content into downstream tasks...