CVE-2026-54327

Pi is a minimal terminal coding harness. From 0.74.0 until 0.78.1, Pi stored API keys and OAuth credentials in auth.json. A race condition in the file write path could briefly create or rewrite this file with permissions derived from the process umask before tightening the file to owner-only...

CVE-2026-54326

Pi is a minimal terminal coding harness. From 0.74.0 until 0.78.1, Pi HTML exports render session Markdown into a static HTML file. It did not consistently reject unsafe Markdown link and image URL schemes. In versions with scheme filtering, C0 control characters in the URL scheme could bypass th...

CVE-2026-56696

CVE-2026-56696 affects OpenHarness; the /issue and /pr_comments slash commands lack remote_invocable=False protection. This allows remote attackers to write attacker-controlled Markdown into project context files (.openharness/issue.md and .openharness/pr_comments.md). The injected content is sub...

CVE-2026-40502

OpenHarness prior to commit dd1d235 contains a command injection vulnerability that allows remote gateway users with chat access to invoke sensitive administrative commands by exploiting insufficient distinction between local-only and remote-safe commands in the gateway handler. Attackers can...

CVE-2026-40503

OpenHarness prior to commit dd1d235 contains a path traversal vulnerability that allows remote gateway users with chat access to read arbitrary files by supplying path traversal sequences to the /memory show slash command. Attackers can manipulate the path input parameter to escape the project...

OESA-2026-2545 opensc security update

OpenSC provides a set of libraries and utilities to work with smart cards. Its main focus is on cards that support cryptographic operations, and facilitate their use in security applications such as authentication, mail encryption and digital signatures. OpenSC implements the standard APIs to sma...

PT-2026-44853

Improper handling of physical conditions in the bike-shutdown control of the Indian Motorcycle Scout Bobber + Tech 2025 model year allows a physical attacker with access to the Wireless Control Module WCM wiring harness to bypass the anti-theft shutdown. The WCM signals shutdown to a peer ECU via...

EUVD-2026-32454

In the Linux kernel, the following vulnerability has been resolved: ntfs3: add buffer boundary checks to rununpack rununpack checks runbuf runlast at the top of the while loop but then reads sizesize and offsetsize bytes via rununpacks64 without verifying they fit within the remaining buffer. A...

mythos-preview

🜲 Mythos Preview Multi-agent vulnerability discovery harn...

Malicious code in harness-skil (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector e03ab8467953cd2233e07e792a33c7df7be2c99c66da3b814538a169337b93e6 The package's install.js wired to an npm install lifecycle hook requires childprocess, fs, and https, then issues an https.get to a...

FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing

Library fuzzing is essential for hardening the software supply chain, but adopting it at scale remains expensive. Practitioners still spend substantial effort on environment setup, struggle to generate harnesses that respect intricate API constraints, and lack reliable means to tell genuine libra...

Defense at AI speed: Microsoft’s new multi-model agentic security system tops leading industry benchmark

In this article 1. AI-powered vulnerability discovery at hyper-scale 2. Codename: MDASH—Microsoft Security’s new multi-model agentic scanning harness 3. Using codename MDASH for security research 4. The 5.12.2026 Patch Tuesday cohort 5. Two deep dives 1. CVE-2026-33827—Remote unauthenticated UAF ...

IPI-Proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents against Indirect Prompt Injection

Web-browsing AI agents are increasingly deployed in enterprise settings under strict whitelists of approved domains, yet adversaries can still influence them by embedding hidden instructions in the HTML pages those domains serve. Existing red-teaming resources fall short of this scenario:...

CVE-2026-7551

HKUDS OpenHarness contains a remote code execution vulnerability in the /bridge slash command that allows remote senders accepted by configuration to execute arbitrary operating system commands. Attackers can invoke the /bridge spawn command with attacker-controlled command text that is forwarded...

CVE-2026-7551 HKUDS OpenHarness Remote Command Execution via /bridge Slash Command

HKUDS OpenHarness contains a remote code execution vulnerability in the /bridge slash command that allows remote senders accepted by configuration to execute arbitrary operating system commands. Attackers can invoke the /bridge spawn command with attacker-controlled command text that is forwarded...

EUVD-2026-26451

HKUDS OpenHarness contains a remote code execution vulnerability in the /bridge slash command that allows remote senders accepted by configuration to execute arbitrary operating system commands. Attackers can invoke the /bridge spawn command with attacker-controlled command text that is forwarded...

CVE-2026-7551

The CVE describes a remote code execution vulnerability in HKUDS OpenHarness exposed via the /bridge command. An attacker-enabled /bridge spawn command can forward attacker-controlled text to the bridge session manager and execute commands through the shared shell subprocess helper, allowing shel...

PT-2026-36203

Name of the Vulnerable Software and Affected Versions HKUDS OpenHarness affected versions not specified Description A remote code execution issue exists in the '/bridge' slash command. Remote senders accepted by the configuration can execute arbitrary operating system commands. This occurs when t...

Symbolic Execution Meets Multi-LLM Orchestration: Detecting Memory Vulnerabilities in Incomplete Rust CVE Snippets

This paper presents a system combining symbolic execution KLEE with a 4-agent multi-LLM architecture for detecting memory vulnerabilities in Rust unsafe code. A central challenge we address is the incomplete-code problem: CVE database entries provide only isolated code snippets that lack struct...

Synthesizing Multi-Agent Harnesses for Vulnerability Discovery

LLM agents have begun to find real security vulnerabilities that human auditors and automated fuzzers missed for decades, in source-available targets where the analyst can build and instrument the code. In practice the work is split among several agents, wired together by a harness: the program...