CVE-2025-51860

CVE-2025-51860 Vulnerability description TelegAI, a web application for constructing and chatting with AI Characters, is vulnerable to Stored Cross-Site Scripting XSS in its chat component and character container component. An attacker can achieve arbitrary client-side script execution by craftin...

meta-ai-support-prompt

Meta AI Support Assistant System Prompt Extracted system prompt from Meta's AI Support Assistant on June 1, 2026. Files system-prompt.md — Extracted system prompt ⚠️ Disclaimer & Legal Notice Purpose This repository is published strictly for educational and authorized security research purposes...

delirium-ai-safety-benchmark

Delirium AI Safety Benchmark A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion ACE and related liminal attack vectors. Delirium is not an exploitation tool. It is a standardized benchmark designed to detect the precise moment when a language model's attention...

prompt-injection-email-samples

Prompt-Injection Email Samples A small, open test set of emails for checking whether your email security controls and AI mailbox assistants handle indirect prompt injection : instructions hidden in an email that try to hijack an AI assistant when it reads, summarizes or acts on that email. The se...

Detecting and Mitigating Query-Based System Prompt Leakage Attacks

Large Language Models LLMs rely on proprietary system prompts to enforce task directives, safety policies, and access controls. These prompts are vulnerable to query-based leakage attacks, where black-box adversaries extract confidential instructions through adaptive, multi-turn interactions...

Black-Box Red-Teaming of Multi-Agent Systems Via Reinforcement Learning

Large language model LLM agents are increasingly deployed in multi-agent systems MAS to accomplish complex tasks. Prior black-box red-teaming attacks mainly focus on single agents, but we find that these methods are far less effective in MAS, where multiple sub-agents may not directly interact wi...

EUVD-2026-102914

SparkyFitness is a self-hosted, AI-powered health and fitness tracker for families. Prior to 1.6.0, SparkyFitnessServer/services/chatService.ts and SparkyFitnessServer/services/labelScanService.ts do not validate destinations supplied in custom AI service settings. An authenticated user saves a...

CVE-2026-102923: Server-Side Request Forgery (SSRF)

SparkyFitness is a self-hosted, AI-powered health and fitness tracker for families. Prior to 1.6.0, SparkyFitnessServer/services/chatService.ts and SparkyFitnessServer/services/labelScanService.ts do not validate destinations supplied in custom AI service settings. An authenticated user saves a...

PT-2026-115631

SparkyFitness is a self-hosted, AI-powered health and fitness tracker for families. Prior to 1.6.0, SparkyFitnessServer/services/chatService.ts and SparkyFitnessServer/services/labelScanService.ts do not validate destinations supplied in custom AI service settings. An authenticated user saves a...

CodeWithCJ SparkyFitness: Server Request Forgery Vulnerability

Versions of CodeWithCJ SparkyFitness prior to 1.6.0 contain a server-side request forgeing vulnerability. This vulnerability arises from the lack of validation for the target addresses provided in the custom AI service settings in files SparkyFitnessServer/services/chatService.ts and...

PraisonAI: Prompt Injection Defense Bypassed for HIGH-Level Threats

SummaryInjection Defense is a purpose-built prompt injection defense layer. It scans LLM inputs through six detection categories: instruction overrides, authority claims, boundary manipulation, obfuscation, financial manipulation, and self-harm instructions.The defense is misconfigured by default...

PYSEC-2026-4255 PraisonAI: Prompt Injection Defense Bypassed for HIGH-Level Threats

Summary Injection Defense is a purpose-built prompt injection defense layer. It scans LLM inputs through six detection categories: instruction overrides, authority claims, boundary manipulation, obfuscation, financial manipulation, and self-harm instructions. The defense is misconfigured by...

Prompt Injection Bypass

PraisonAI is vulnerable to a Prompt Injection Bypass. The vulnerability is due to the block threshold defaulting to CRITICAL severity, which allows an attacker to submit instruction override or financial manipulation prompts that evade blocking, potentially enabling system prompt extraction and...

PraisonAI: Prompt Injection Defense Bypassed for HIGH-Level Threats

Summary Injection Defense is a purpose-built prompt injection defense layer. It scans LLM inputs through six detection categories: instruction overrides, authority claims, boundary manipulation, obfuscation, financial manipulation, and self-harm instructions. The defense is misconfigured by...

PT-2026-87136

A malicious webpage could repeatedly trigger external URL schemes, causing system prompts or external application launches. This could make Firefox for iOS temporarily unusable until the page is closed. This vulnerability was fixed in Firefox for iOS 155.1...

EUVD-2026-60966

CodeWhale: Project config instructions override enables arbitrary file read into AI system prompt via cloned repository...

NPM: CodeWhale: Project config `instructions` override enables arbitrary file read into AI system prompt via cloned repository

NPM: CodeWhale: Project config instructions override enables arbitrary file read into AI system prompt via cloned repository vulnerability discovered by ? in WordPress Npm deepseek-tui versions = 0.8.8, 0.8.41...

GHSA-62F5-CP2P-VQ95 CodeWhale: Project config `instructions` override enables arbitrary file read into AI system prompt via cloned repository

Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 43563356b98c6b993085554da82e77370160a31c. Users should upgrade to 0.8.64 or later. The original reporter analysis is...

CodeWhale: Project config `instructions` override enables arbitrary file read into AI system prompt via cloned repository

Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 43563356b98c6b993085554da82e77370160a31c. Users should upgrade to 0.8.64 or later. The original reporter analysis is...

NPM: CodeWhale: Project config `instructions` override enables arbitrary file read into AI system prompt via cloned repository

NPM: CodeWhale: Project config instructions override enables arbitrary file read into AI system prompt via cloned repository vulnerability discovered by ? in WordPress Npm codewhale versions = 0.8.41, 0.8.64...