CVE-2026-19645

IBM MQ Agent CD: v1.0.0, v1.0.1, v2.0.0, v2.0.1 An authenticated user with a valid session cookie can submit arbitrarily large or computationallyexpensive requests that cause the LLM agent workers to be held for extended periods — rangingfrom tens of seconds to over ten minutes per request. When...

EUVD-2026-71260

IBM Langflow OSS 1.0.0 through 1.11.2 allows an authenticated attacker to read arbitrary files from the server filesystem — including server secret material secretkey, JWT signing keys, the application database, /proc/self/environ, and other tenants' upload directories — by supplying absolute pat...

CVE-2026-19645 Multiple vulnerabilities in IBM MQ Agent images

IBM MQ Agent CD: v1.0.0, v1.0.1, v2.0.0, v2.0.1 An authenticated user with a valid session cookie can submit arbitrarily large or computationallyexpensive requests that cause the LLM agent workers to be held for extended periods — rangingfrom tens of seconds to over ten minutes per request. When...

CVE-2026-19645

IBM MQ Agent images (CD versions v1.0.0, v1.0.1, v2.0.0, v2.0.1) are affected by a vulnerability where an authenticated user with a valid session cookie can submit arbitrarily large or computationally expensive requests that hold LLM agent workers for extended periods—ranging from tens of seconds...

CVE-2026-19645 Multiple vulnerabilities in IBM MQ Agent images

IBM MQ Agent CD: v1.0.0, v1.0.1, v2.0.0, v2.0.1 An authenticated user with a valid session cookie can submit arbitrarily large or computationallyexpensive requests that cause the LLM agent workers to be held for extended periods — rangingfrom tens of seconds to over ten minutes per request. When...

EUVD-2026-71259

IBM MQ Agent CD: v1.0.0, v1.0.1, v2.0.0, v2.0.1 An authenticated user with a valid session cookie can submit arbitrarily large or computationallyexpensive requests that cause the LLM agent workers to be held for extended periods — rangingfrom tens of seconds to over ten minutes per request. When...

CVE-2026-85694 LaVague 0.2.35 Remote Code Execution via eval extraction

LaVague 0.2.35 contains a remote code execution vulnerability in PythonFromMarkdownExtractor.extractasobject that evaluates untrusted language model output derived from web page content. Attackers can inject malicious Python code through web pages using indirect prompt injection to execute...

CVE-2026-85694

LaVague 0.2.35 is vulnerable to remote code execution via its PythonFromMarkdownExtractor.extract_as_object function, which uses eval on untrusted language model output derived from web page content. An attacker can perform indirect prompt injection through a web page to inject malicious Python c...

EUVD-2026-71143

LaVague 0.2.35 contains a remote code execution vulnerability in PythonFromMarkdownExtractor.extractasobject that evaluates untrusted language model output derived from web page content. Attackers can inject malicious Python code through web pages using indirect prompt injection to execute...

CVE-2026-85694 LaVague 0.2.35 Remote Code Execution via eval extraction

LaVague 0.2.35 contains a remote code execution vulnerability in PythonFromMarkdownExtractor.extractasobject that evaluates untrusted language model output derived from web page content. Attackers can inject malicious Python code through web pages using indirect prompt injection to execute...

augustus v0.14.24

Augustus - LLM vulnerability scanner for prompt injection, jailbreak, and adversarial attack testing Augustus - LLM Vulnerability Scanner Test large language models against 210+ adversarial attacks covering prompt injection, jailbreaks, encoding exploits, and data extraction. Augustus is a Go-bas...

noir v1.3.1

Hunt every Endpoint in your code, expose Shadow APIs, map the Attack Surface. Documentation • Installation • Usage • Github Action • Contributing • Changelog Noir is a SAST tool that reads source code and extracts the endpoints an application exposes — paths, methods, parameters, headers, cookies...

skill-scanner v2.0.14

Skill Scanner A best-effort security scanner for AI Agent Skills that detects prompt injection, data exfiltration, and malicious code patterns. It combines pattern-based detection YAML + YARA-X, AST and dataflow analysis , an optional LLM-as-a-judge , and a bounded CEL decision layer over typed...

CONTINUITY: Security-Context Contracts for Composable LLM Agent Controls

LLM agent systems increasingly combine provenance tracking, authorization, policy enforcement, protocol adapters, and execution controls. However, individually correct security mechanisms do not necessarily compose into an end-to-end secure system: security-critical context may be dropped, widene...

PT-2026-85590

IBM MQ Agent CD: v1.0.0, v1.0.1, v2.0.0, v2.0.1 An authenticated user with a valid session cookie can submit arbitrarily large or computationallyexpensive requests that cause the LLM agent workers to be held for extended periods — rangingfrom tens of seconds to over ten minutes per request. When...

CVE-2026-85668: External Control of File Name or Path

Xinference affected commit 4a94832, v3.x contains an unauthenticated arbitrary-path file read vulnerability in the POST /v1/models/llm/auto-register endpoint, which accepts a caller-supplied modelpath parameter without authentication or path confinement. The endpoint reads and parses config.json,...

Cost-Aware Hierarchical Multi-Agent Ransomware Detection and Family Attribution

Ransomware detection and family attribution require analysis of different modalities because it can use packing, obfuscation, process manipulation and runtime evasion techniques. However, conventional multimodal usually uses all available modalities for every sample resulting in unnecessary...

The History Is the Detector: Executing CVE Patch History, End-To-End

Public vulnerability databases collect rich information about known software flaws, including their weakness types, affected components, and related patches. Fixing commits provide the exact code changes that removed these flaws. While these records capture why the original code was unsafe, they...

TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors

Current LLM safety benchmarks largely rely on binary metrics, overlooking how models respond to harmful prompts with varying threat implicitness. We introduce TIER, a Threat Implicitness Benchmark for behavioral safety evaluation of LLMs. TIER covers four risk domains and four threat levels, from...

IDAssist v2.3.0

IDAssist AI-Powered Reverse Engineering Plugin for IDA Pro Author: Jason Tang Description IDAssist is an IDA Pro plugin that integrates LLM-powered analysis directly into IDA's interface, providing AI-assisted binary reverse engineering through configurable LLM providers, semantic knowledge graph...