EUVD-2026-65735

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...

CVE-2026-78379 Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents Tools

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...

CVE-2026-55580 mcp-shell — Security Disabled by Default in Bare-Binary Deploy Path + Shell Interpreter in Secure-Mode Allowlist

mcp-shell is an MCP server for running shell commands securely, auditably, and on demand. Prior to 0.6.0, config.go initializes Security.Enabled to false, and when MCPSHELLSECCONFIGFILE is unset, main.go starts the documented bare-binary deployment without a security policy...

CVE-2026-55580 mcp-shell — Security Disabled by Default in Bare-Binary Deploy Path + Shell Interpreter in Secure-Mode Allowlist

mcp-shell is an MCP server for running shell commands securely, auditably, and on demand. Prior to 0.6.0, config.go initializes Security.Enabled to false, and when MCPSHELLSECCONFIGFILE is unset, main.go starts the documented bare-binary deployment without a security policy...

GHSA-CFXV-8FW8-RWPV praisonaiagents: ast_grep_rewrite rewrites arbitrary files without the @require_approval gate enforced on every sibling mutation tool

Target: PraisonAI MervinPraison/PraisonAI Affected component: praisonaiagents/tools/astgreptool.py — astgreprewrite Affected versions: master at ce97667156a116c50b4a3d1aa21e09f048903fda; reproduced against the current praisonaiagents PyPI release praisonaiagents --rewrite --lang --update-all line...

Missing Authentication for Critical Function

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

Design-and-Evaluation-of-an-MCP-Governed-Pentest-Agent

Design-and-Evaluation-of-an-MCP-Governed-Pentest-Agent Dissert...

PT-2026-81212

My two cents is that this democratises AI-availability and Privacy. Doom on hardware Y is an existence proof and dies there! For fulfilling your curiosity running a glm-5.1 UD-IQ1 M on one Mac studio M3 ultra plus a iogpu sysctl made us at byteray CVE-2026-55706 a 27-year old bug on OpenBSD just ...

Prompt Structure Redistributes, Not Reduces: An Empirical Analysis of Security-Weaknesses in LLM-Generated Python Code

Large Language Models LLMs increasingly generate code from natural-language prompts, making prompt engineering a key mechanism for shaping the security of generated software. Structured and security-oriented prompts are widely used to encourage safer code, yet their effects extend beyond whether...

PT-2026-81208

U-Boot before 2026.10-rc3 contains an out-of-bounds write vulnerability in read slotted partition that fails to validate image size against partition bounds. Attackers with physical access can supply crafted boot media with oversized headers to write past the load buffer into bootloader memory on...

PT-2026-81205

Name of the Vulnerable Software and Affected Versions U-Boot versions prior to 2026.10-rc3 Description An out-of-bounds write occurs in the net defragment function within net/net.c when CONFIG IP DEFRAG is enabled. Remote attackers can trigger this by sending a crafted IP fragment with a non-zero...

PT-2026-81206

Name of the Vulnerable Software and Affected Versions U-Boot versions prior to 2026.10-rc5 Description An out-of-bounds write exists in the RLE8 bitmap decoder within the video subsystem. The video display rle8 bitmap function in drivers/video/video bmp.c decodes run-length encoded streams direct...

Towards LLM-Enhanced Android Taint Analysis

Taint analysis is a fundamental technique for detecting sensitive data leaks in Android apps. However, traditional static tools, such as FlowDroid, still face well-known challenges due to the complexity of accurately modeling the Android framework. In this paper, we investigate whether...

PT-2026-81200

My two cents is that this democratises AI-availability and Privacy. Doom on hardware Y is an existence proof and dies there! For fulfilling your curiosity running a glm-5.1 UD-IQ1 M on one Mac studio M3 ultra plus a iogpu sysctl made us at byteray CVE-2026-55706 a 27-year old bug on OpenBSD just ...

Important: Red Hat Security Advisory: Red Hat Enterprise Linux AI 3.4.4 enhancement update

Updated Red Hat Enterprise Linux AI 3.4.4 container images are now available. Red Hat® Enterprise Linux® AI is a foundation model platform to seamlessly develop, test, and run Granite family large language models LLMs for enterprise applications. This update provides the latest Red Hat Enterprise...

NeuroSploit v4.0.0

🧠 NeuroSploit v4.0.0 Autonomous, multi-model penetration-testing harness — Rust, CLI-only. by Joas A Santos & Red Team Leaders ⭐ If this is useful, star the repo — it helps a lot. 📖 New here? Read thefull Tutorial & User Guide → — every mode, flag, config and example explained. Version-by-version...

Verification-Guided Specification Synthesis with Large Language Models for Intrusion Detection Rules

Attacks against Internet-connected IoT devices continue to increase; however, transforming observed attack traffic into deployable intrusion detection system IDS rules remains largely a manual process. Recent studies have explored using large language models LLMs to generate IDS rules; nonetheles...

Names Can Hurt: Spotting Slopsquatting Risks Caused by Package Name Hallucinations in Local Coding LLMs

When a code generating language model fabricates a Python package name, an adversary who has pre-registered that name on PyPI can convert that hallucination into a supply chain compromise. This event has been termed as 'slopsquatting'. We propose a two layer detector to counter this issue. The...

AgentFlow: A Flow-Centric Policy Language and Framework for Securing LLM Agent Systems

LLM agents increasingly read untrusted content, invoke external tools, access private data, and delegate work to other agents. Harm often arises not from a single unsafe action but from the flow of sensitive data across a sequence of otherwise plausible steps. We present AgentFlow, a flow-centric...

Towards Automated Cyber Threat Intelligence Elicitation in Underground Forums

Cyber threat intelligence from underground forums has traditionally relied on passive monitoring. However, as users have become more aware of large-scale data collection, valuable intelligence has become increasingly rare in open forums, often migrating instead to private or harder-to-reach space...