1941 matches found
CVE-2025-64320
Improper Neutralization of Input Used for LLM Prompting vulnerability in Salesforce Agentforce Vibes Extension allows Code Injection.This issue affects Agentforce Vibes Extension: before 3.2.0...
GHSA-CRVM-XJHM-9H29 OctoPrint vulnerable to XSS in Action Commands Notification and Prompt
Impact OctoPrint versions up to and including 1.11.3 are affected by a vulnerability that allows injection of arbitrary HTML and JavaScript into Action Command notification and prompt popups generated by the printer. An attacker who successfully convinces a victim to print a specially crafted fil...
OctoPrint vulnerable to XSS in Action Commands Notification and Prompt
Impact OctoPrint versions up to and including 1.11.3 are affected by a vulnerability that allows injection of arbitrary HTML and JavaScript into Action Command notification and prompt popups generated by the printer. An attacker who successfully convinces a victim to print a specially crafted fil...
git: Git does not sanitize URLs when asking for credentials interactively
A flaw was found in Git. This vulnerability occurs when Git requests credentials via a terminal prompt, for example, without the use of a credential helper. During this process, Git displays the host name for which the credentials are needed, but any URL-encoded parts are decoded and displayed...
PT-2025-45034
Name of the Vulnerable Software and Affected Versions Salesforce Agentforce Vibes Extension versions prior to 3.2.0 Description An issue exists in Salesforce Agentforce Vibes Extension related to improper neutralization of input used for LLM prompting, potentially allowing manipulation of writabl...
PT-2025-45060
Name of the Vulnerable Software and Affected Versions Cursor versions 1.7.28 and below Description Cursor is a code editor designed for programming with AI. An input validation issue within Cursor’s MCP server installation allows maliciously crafted deep-links to circumvent standard security...
AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models
Large Language Models LLMs remain vulnerable to jailbreaking attacks where adversarial prompts elicit harmful outputs, yet most evaluations focus on single-turn interactions while real-world attacks unfold through adaptive multi-turn conversations. We present AutoAdv, a training-free framework fo...
ctf-competition-2025
SINF25 CTF Competition Writeups This repository cont...
Jailbreak Mimicry: Automated Discovery of Narrative-Based Jailbreaks for Large Language Models
Large language models LLMs remain vulnerable to sophisticated prompt engineering attacks that exploit contextual framing to bypass safety mechanisms, posing significant risks in cybersecurity applications. We introduce Jailbreak Mimicry, a systematic methodology for training compact attacker mode...
The Trojan Example: Jailbreaking LLMs through Template Filling and Unsafety Reasoning
Large Language Models LLMs have advanced rapidly and now encode extensive world knowledge. Despite safety fine-tuning, however, they remain susceptible to adversarial prompts that elicit harmful content. Existing jailbreak techniques fall into two categories: white-box methods e.g., gradient-base...
Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses
Multimodal large language models MLLMs comprise of both visual and textual modalities to process vision language tasks. However, MLLMs are vulnerable to security-related issues, such as jailbreak attacks that alter the model's input to induce unauthorized or harmful responses. The incorporation o...
Active Honeypot Guardrail System: Probing and Confirming Multi-Turn LLM Jailbreaks
Large language models LLMs are increasingly vulnerable to multi-turn jailbreak attacks, where adversaries iteratively elicit harmful behaviors that bypass single-turn safety filters. Existing defenses predominantly rely on passive rejection, which either fails against adaptive attackers or overly...
aether
Aether - Adaptive Exploit & Threat Hunting Engine for EVM-base...
September 9, 2025—KB5065432 (OS Build 20348.4171)
None None...
September 9, 2025—Hotpatch KB5065474 (OS Build 26100.6508) for Windows Server
None None...
API Attack Awareness: Injection Attacks in APIs – Old Threat, New Surface
Injection attacks are among the oldest tricks in the attacker playbook. And yet they persist. The problem is that the core weakness, trusting user inputs too much, keeps resurfacing in new forms. As organizations have shifted to API-driven architectures and integrated AI systems that consume...
A2AS: Agentic AI Runtime Security and Self-Defense
The A2AS framework is introduced as a security layer for AI agents and LLM-powered applications, similar to how HTTPS secures HTTP. A2AS enforces certified behavior, activates model self-defense, and ensures context window integrity. It defines security boundaries, authenticates prompts, applies...
EUVD-2020-2195
Malware in sbrugna...