CVE-2024-45858

An arbitrary code execution vulnerability exists in versions 0.2.9 up to 0.5.10 of the Guardrails AI Guardrails framework because of the way it validates XML files. If a victim user loads a maliciously crafted XML file containing Python code, the code will be passed to an eval function, causing i...

CVE-2024-45858

An arbitrary code execution vulnerability exists in versions 0.2.9 up to 0.5.10 of the Guardrails AI Guardrails framework because of the way it validates XML files. If a victim user loads a maliciously crafted XML file containing Python code, the code will be passed to an eval function, causing i...

CVE-2024-45858

An arbitrary code execution vulnerability exists in versions 0.2.9 up to 0.5.10 of the Guardrails AI Guardrails framework because of the way it validates XML files. If a victim user loads a maliciously crafted XML file containing Python code, the code will be passed to an eval function, causing i...

CVE-2024-45858

CVE-2024-45858 affects Guardrails AI Guardrails framework versions 0.2.9–0.5.10. The root cause is improper validation of XML files, where loading a malicious XML containing Python code causes the code to be passed to eval and executed on the user’s machine. The vulnerability enables arbitrary co...

PT-2024-31815

Name of the Vulnerable Software and Affected Versions Guardrails AI Guardrails framework versions 0.2.9 through 0.5.10 Description An arbitrary code execution issue exists due to the way the Guardrails AI Guardrails framework validates XML files. If a maliciously crafted XML file containing Pytho...

Guardrails 安全漏洞

Guardrails is a Python framework open-sourced by Guardrails AI. A security vulnerability exists in Guardrails versions 0.2.9 through 0.5.0 and earlier, which stems from its improper validation of an XML file, such that if a victim loads an XML file containing malicious Python code, the code will ...

CVE-2024-45858: Improper Neutralization of Directives in Dynamically Evaluated Code

An arbitrary code execution vulnerability exists in versions 0.2.9 up to 0.5.10 of the Guardrails AI Guardrails framework because of the way it validates XML files. If a victim user loads a maliciously crafted XML file containing Python code, the code will be passed to an eval function, causing i...

XML Entity Expansion (XXE)

guardrails-ai is vulnerable to XML Entity Expansion XXE. The vulnerability is due to consuming RAIL documents from external sources, which may cause leakage of internal file data via the SYSTEM entity...

Guardrails AI vulnerable to Improper Restriction of XML External Entity Reference

RAIL documents are an XML-based format invented by Guardrails AI to enforce formatting checks on LLM outputs. Guardrails users that consume RAIL documents from external sources are vulnerable to XXE, which may cause leakage of internal file data via the SYSTEM entity...

GHSA-F8HX-F4XW-C646 Guardrails AI vulnerable to Improper Restriction of XML External Entity Reference

RAIL documents are an XML-based format invented by Guardrails AI to enforce formatting checks on LLM outputs. Guardrails users that consume RAIL documents from external sources are vulnerable to XXE, which may cause leakage of internal file data via the SYSTEM entity...

CVE-2024-6961

RAIL documents are an XML-based format invented by Guardrails AI to enforce formatting checks on LLM outputs. Guardrails users that consume RAIL documents from external sources are vulnerable to XXE, which may cause leakage of internal file data via the SYSTEM entity...

CVE-2024-6961 XXE in Guardrails AI when consuming RAIL documents

RAIL documents are an XML-based format invented by Guardrails AI to enforce formatting checks on LLM outputs. Guardrails users that consume RAIL documents from external sources are vulnerable to XXE, which may cause leakage of internal file data via the SYSTEM entity...

CVE-2024-6961 XXE in Guardrails AI when consuming RAIL documents

RAIL documents are an XML-based format invented by Guardrails AI to enforce formatting checks on LLM outputs. Guardrails users that consume RAIL documents from external sources are vulnerable to XXE, which may cause leakage of internal file data via the SYSTEM entity...

CVE-2024-6961

CVE-2024-6961 describes an XML External Entity (XXE) vulnerability in Guardrails AI when consuming RAIL documents from external sources, potentially allowing leakage of internal file data via the SYSTEM entity. The affected component is Guardrails AI and its RAIL document handling; the underlying...

CVE-2024-6961: Improper Restriction of XML External Entity Reference

RAIL documents are an XML-based format invented by Guardrails AI to enforce formatting checks on LLM outputs. Guardrails users that consume RAIL documents from external sources are vulnerable to XXE, which may cause leakage of internal file data via the SYSTEM entity...

PT-2024-38000

Name of the Vulnerable Software and Affected Versions Guardrails AI affected versions not specified Description The issue concerns RAIL documents, an XML-based format used by Guardrails AI for enforcing formatting checks on LLM outputs. Users who consume RAIL documents from external sources are a...

Prompt Injection Flaw in Vanna AI Exposes Databases to RCE Attacks

Cybersecurity researchers have disclosed a high-severity security flaw in the Vanna.AI library that could be exploited to achieve remote code execution vulnerability via prompt injection techniques. The vulnerability, tracked as CVE-2024-5565 CVSS score: 8.1, relates to a case of prompt injection...

Azure Service Tags Vulnerability: Microsoft Warns of Potential Abuse by Hackers

Microsoft is warning about the potential abuse of Azure Service Tags by malicious actors to forge requests from a trusted service and get around firewall rules, thereby allowing them to gain unauthorized access to cloud resources. "This case does highlight an inherent risk in using service tags a...

AI jailbreaks: What they are and how they can be mitigated

Generative AI systems are made up of multiple components that interact to provide a rich user experience between the human and the AI models. As part of a responsible AI approach, AI models are protected by layers of defense mechanisms to prevent the production of harmful content or being used to...

FTC Fines Mental Health Startup Cerebral $7 Million for Major Privacy Violations

The U.S. Federal Trade Commission FTC has ordered mental telehealth company Cerebral from using or disclosing personal medical data for advertising purposes. It has also been fined more than $7 million over charges that it revealed users' sensitive personal health information and other data to...