Showing Posts About

2024

Multi-Chain Prompt Injection Attacks

Multi-chain prompt injection is a novel attack technique targeting complex LLM applications with multiple chained language models. The technique exploits interactions between LLM chains to bypass safeguards and propagate malicious content through entire systems. A sample workout planner application demonstrates how attackers can manipulate multi-chain LLM workflows to inject and propagate adversarial prompts across different processing stages.

  • 10 Apr 2024

Abusing search permissions on Docker directories for privilege escalation

A privilege escalation vulnerability was discovered in Docker environments where the /var/lib/docker directory has search permissions for other users. Low-privileged attackers can access container filesystems by exploiting these permissions. By modifying container startup scripts and leveraging host reboot capabilities, attackers can potentially gain root access on the host system.

Domain-specific prompt injection detection

A domain-specific machine learning approach was developed to detect prompt injection attacks in job application contexts using a fine-tuned DistilBERT classifier. The model was trained on a custom dataset of job applications and prompt injection examples, achieving approximately 80% accuracy in identifying potential injection attempts. The research highlights the challenges of detecting prompt injection in large language models and emphasizes that such detection methods are just one part of a comprehensive security strategy.

  • 29 Feb 2024

Binary Exploitation for SPECIAL Occasions: Privilege Escalation in z/OS

This article explores a privilege escalation technique in z/OS mainframe systems by manipulating the Accessor Environment Element (ACEE). The technique involves creating an APF-authorized assembly program that modifies user flags in memory to gain SPECIAL privileges. The exploit demonstrates how low-level memory structures and system internals can be leveraged to escalate system access.

  • 29 Feb 2024

The Hidden Depths of Mainframe Application Testing: More Than (Green) Screen-Deep

Mainframe application security testing requires looking beyond surface-level "green screen" interfaces. The article explores three key vulnerability areas in mainframe environments: application breakouts that allow unauthorized transaction access, surrogate chaining that can bypass environment segregation controls, and downstream misconfigurations in database and system components. Comprehensive security assessments must take a holistic approach to mainframe application testing.

Should you let ChatGPT control your browser?

This article explores the security risks of granting Large Language Models (LLMs) control over web browsers. Two attack scenarios demonstrate how prompt injection vulnerabilities can be exploited to hijack browser agents and perform malicious actions. The article highlights critical security challenges in LLM-driven browser automation and proposes potential defense strategies.

eLinkSmart - Unlocking Bluetooth LE padlocks with polite requests

A critical security analysis of eLinkSmart Bluetooth padlocks revealed multiple severe vulnerabilities. The locks have hardcoded encryption keys, an insecure web API with SQL injection flaws, and weak authentication controls. These vulnerabilities allow attackers to unlock any lock within Bluetooth range and access sensitive user information.

  • 2 Feb 2024

runc working directory breakout (CVE-2024-21626)

A critical vulnerability in runc (CVE-2024-21626) allows attackers to break out of container filesystems by exploiting a file descriptor leak. The flaw enables setting a container's working directory to the host filesystem, potentially granting unauthorized access to host systems in Kubernetes and containerized environments. Attackers can leverage this vulnerability to access host filesystems, execute malicious code, and potentially compromise multi-tenant Kubernetes clusters.