EUVD-2026-20773

MemProcFS before 5.17 contains multiple unsafe library-loading patterns that enable DLL and shared-library hijacking across six attack surfaces, including bare-name LoadLibraryU and dlopen calls without path qualification for vmmpyc, libMSCompression, and plugin DLLs. An attacker who places a...

ACIArena: Toward Unified Evaluation for Agent Cascading Injection

Collaboration and information sharing empower Multi-Agent Systems MAS but also introduce a critical security risk known as Agent Cascading Injection ACI. In such attacks, a compromised agent exploits inter-agent trust to propagate malicious instructions, causing cascading failures across the...

Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions

Retrieval-augmented generation RAG significantly enhances large language models LLMs but introduces novel security risks through external knowledge access. While existing studies cover various RAG vulnerabilities, they often conflate inherent LLM risks with those specifically introduced by RAG. I...

CVE-2026-40031 MemProcFS < 5.17 DLL/Shared Library Hijacking

MemProcFS before 5.17 contains multiple unsafe library-loading patterns that enable DLL and shared-library hijacking across six attack surfaces, including bare-name LoadLibraryU and dlopen calls without path qualification for vmmpyc, libMSCompression, and plugin DLLs. An attacker who places a...

CVE-2026-40031

MemProcFS before 5.17 contains multiple unsafe library-loading patterns that enable DLL and shared-library hijacking across six attack surfaces, including bare-name LoadLibraryU and dlopen calls without path qualification for vmmpyc, libMSCompression, and plugin DLLs. An attacker who places a...

CVE-2026-40031 MemProcFS < 5.17 DLL/Shared Library Hijacking

MemProcFS before 5.17 contains multiple unsafe library-loading patterns that enable DLL and shared-library hijacking across six attack surfaces, including bare-name LoadLibraryU and dlopen calls without path qualification for vmmpyc, libMSCompression, and plugin DLLs. An attacker who places a...

Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection across Attack Surfaces and Model Safety Tiers

We present a stage-decomposed analysis of prompt injection attacks against five frontier LLM agents. Prior work measures task-level attack success rate ASR; we localize the pipeline stage at which each model's defense activates. We instrument every run with a cryptographic canary token...

CVE-2026-32024

OpenClaw versions prior to 2026.2.22 contain a symlink traversal vulnerability in avatar handling that allows attackers to read arbitrary files outside the configured workspace boundary. Remote attackers can exploit this by requesting avatar resources through gateway surfaces to disclose local...

CVE-2026-33401

Wallos is an open-source, self-hostable personal subscription tracker. Prior to version 4.7.0, the patch introduced in commit e8a513591 CVE-2026-30840 added SSRF protection to notification test endpoints but left three additional attack surfaces unprotected: the AI Ollama host parameter, the AI...

CVE-2026-32024

OpenClaw versions prior to 2026.2.22 contain a symlink traversal vulnerability in avatar handling that allows attackers to read arbitrary files outside the configured workspace boundary. Remote attackers can exploit this by requesting avatar resources through gateway surfaces to disclose local...

CVE-2026-32024

OpenClaw versions prior to 2026.2.22 contain a symlink traversal vulnerability in avatar handling that allows attackers to read arbitrary files outside the configured workspace boundary. Remote attackers can exploit this by requesting avatar resources through gateway surfaces to disclose local...

EUVD-2026-13296

OpenClaw versions prior to 2026.2.22 contain a symlink traversal vulnerability in avatar handling that allows attackers to read arbitrary files outside the configured workspace boundary. Remote attackers can exploit this by requesting avatar resources through gateway surfaces to disclose local...

CVE-2026-32024

OpenClaw (npm) versions prior to 2026.2.22 are affected by a symlink traversal vulnerability in avatar handling that lets remote attackers read arbitrary files outside the configured workspace boundary by requesting avatar resources through gateway surfaces. The issue affects the openclaw package...

CVE-2026-32024 OpenClaw < 2026.2.22 - Symlink Traversal in Avatar Handling

OpenClaw versions prior to 2026.2.22 contain a symlink traversal vulnerability in avatar handling that allows attackers to read arbitrary files outside the configured workspace boundary. Remote attackers can exploit this by requesting avatar resources through gateway surfaces to disclose local...

CVE-2026-32024: Improper Link Resolution Before File Access

OpenClaw versions prior to 2026.2.22 contain a symlink traversal vulnerability in avatar handling that allows attackers to read arbitrary files outside the configured workspace boundary. Remote attackers can exploit this by requesting avatar resources through gateway surfaces to disclose local...

OpenClaw: Command-authorized non-owners could reach owner-only `/config` and `/debug` surfaces

Summary OpenClaw documented /config and /debug as owner-only commands, but the command handlers checked only whether the sender was command-authorized. A lower-trust sender who was intentionally allowed to run commands could still reach privileged configuration and debugging surfaces. Impact This...

GHSA-R7VR-GR74-94P8 OpenClaw: Command-authorized non-owners could reach owner-only `/config` and `/debug` surfaces

Summary OpenClaw documented /config and /debug as owner-only commands, but the command handlers checked only whether the sender was command-authorized. A lower-trust sender who was intentionally allowed to run commands could still reach privileged configuration and debugging surfaces. Impact This...

Security Considerations for Artificial Intelligence Agents

This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by Perplexity's experience operating general-purpose agentic...

What Interoperability in Healthcare Really Means for Security and Privacy

Healthcare interoperability improves care but expands attack surfaces, increasing data exposure, compliance risk, and security challenges across connected systems...

Robust Vision Systems for Connected and Autonomous Vehicles: Security Challenges and Attack Vectors

This article investigates the robustness of vision systems in Connected and Autonomous Vehicles CAVs, which is critical for developing Level-5 autonomous driving capabilities. Safe and reliable CAV navigation undeniably depends on robust vision systems that enable accurate detection of objects,...