HarnessSecurity-Bench: Do Security Mechanisms Really Protect Coding Agent Harnesses?

Coding agent harnesses mediate tool use and authorize actions, yet their security mechanisms and runtime effects remain incompletely characterized. We present HarnessSecurity, the first systematic empirical study and benchmark of open- and closed-source coding agent harnesses. First, we derive a...

vendor-android-cves

vendor-android-cves Collections of our POCs/fuzzing scripts/harness for vendor android CVEs, including those on BlackHat ASIA 2022: https://www.blackhat.com/asia-22/briefings/schedule/the-hidden-rce-surfaces-that-control-the-droids-26083 Update: I've received news about the SMT exploit in this...

Attack Chains, Not Just Attack Surfaces: Why Testing Individual Techniques Misses the Point

Introduction Security teams have gotten pretty good at testing against what can hurt them. Can this EDR agent catch this payload? Will my organization fail the phishing simulation? Does this SIEM rule fire on this particular technique? And, in more mature organizations, this testing happens...

CVE-2026-81348

The My Private Site WordPress plugin before 4.2.3 does not apply its site-privacy access control to certain unauthenticated front-end read surfaces, allowing unauthenticated users to view post content, comments and post URLs from a site the administrator placed behind mandatory login...

CVE-2026-48087

OpenReception’s appointment booking software (before v1.0.2) is vulnerable in the /api/auth/register/{userId} flow. The handler validates the WebAuthn challenge against the registration cookie’s email but does not verify that the URL’s userId belongs to that email. An unauthenticated attacker can...

Joern 4.0.597

Joern is the bug hunter's workbench. With this tool, you can uncover attack surface, sloppy coding practices, and variants of known vulnerabilities using an interactive code analysis shell. Joern supports C, C++, LLVM bitcode, x86 binaries via Ghidra, JVM bytecode via Soot, and Javascript...

Joern 4.0.591

Joern is the bug hunter's workbench. With this tool, you can uncover attack surface, sloppy coding practices, and variants of known vulnerabilities using an interactive code analysis shell. Joern supports C, C++, LLVM bitcode, x86 binaries via Ghidra, JVM bytecode via Soot, and Javascript...

agent-bom v0.97.5

Open security scanner and self-hosted control plane for AI, MCP, and cloud infrastructure. 15 package ecosystems · 16 compliance surfaces · 77 MCP tools · no account required Quick start · Live demo · Docs What it is agent-bom scans repositories, images, and cloud accounts, then correlates what i...

Joern 4.0.583

Joern is the bug hunter's workbench. With this tool, you can uncover attack surface, sloppy coding practices, and variants of known vulnerabilities using an interactive code analysis shell. Joern supports C, C++, LLVM bitcode, x86 binaries via Ghidra, JVM bytecode via Soot, and Javascript...

Double Free

Overview Affected versions of this package are vulnerable to Double Free in ffnvdecstartframesepref in libavcodec/nvdec.c. An attacker can corrupt memory by supplying a crafted video file that drives NVDEC decoding into the “No decoder surfaces left” error path, where the frame-description contex...

A Covert Precision Satellite Communication Framework Assisted by Cooperative IRSs

Satellite communication SatCom, as an effective complement to terrestrial networks, has attracted considerable attention from both academia and industry owing to its wide coverage and high flexibility. However, the inherent openness of satellite links renders them highly vulnerable to...

Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing

Large language model LLM agents are starting to take on routine work in high-performance computing HPC, including monitoring Slurm jobs, diagnosing failed builds, inspecting simulation output, and coordinating scientific workflows. To do this work, an agent commonly acts under its user's...

BythosEngine

Bythos Engine Modular binary analysis & exploit research...

PYSEC-2026-2564 LangChain vulnerable to unsafe deserialization of attacker-controlled objects through overly broad `load()` allowlists

LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load with allowedobjects="all". This does not enable arbitrary Python object deserialization, but it does allow...

Joern 4.0.578

Joern is the bug hunter's workbench. With this tool, you can uncover attack surface, sloppy coding practices, and variants of known vulnerabilities using an interactive code analysis shell. Joern supports C, C++, LLVM bitcode, x86 binaries via Ghidra, JVM bytecode via Soot, and Javascript...

Understanding and Evaluating Claw-Like Agent Security through a Computer-Systems Lens

Claw-like AI agents e.g., OpenClaw are always-on processes with persistent access to credentials, files, tools, and external services. They take on system-level responsibilities -- installing packages, maintaining state, scheduling subtasks, and mediating I/O -- making security failures far more...

LLM Agents Security Duality: A Comprehensive Survey of Self-Security and Empowered Cybersecurity

Large language model LLM agents are rapidly being integrated into real-world systems. Their autonomy and tool-use capabilities generate substantial value while simultaneously expanding the security attack surface. This survey provides a comprehensive overview of the opportunities and challenges o...

Investigating the Security of Modern AI and Cloud Infrastructure

The widespread deployment of Deep Neural Networks and Large Language Models LLMs relies on a foundational assumption of isolation that this dissertation challenges. This work systematically deconstructs security assumptions around AI and modern cloud infrastructure through a taxonomy of interacti...

Insecure Default Initialization of Resource

Overview @kozou/api is a Kozou's own REST layer: serves table CRUD / VIEW reads / OpenAPI from a SchemaContext. Affected versions of this package are vulnerable to Insecure Default Initialization of Resource due to insufficient validation of the Host and Origin headers in the MCP HTTP server,...

Insecure Default Initialization of Resource

Overview @kozou/mcp is a Kozou MCP server for AI agents stdio + HTTP Affected versions of this package are vulnerable to Insecure Default Initialization of Resource due to insufficient validation of the Host and Origin headers in the MCP HTTP server, unbounded request-body buffering, improper...