HardEval: An Execution-Verified Benchmark for AI-Driven Security Hardening and Compliance Remediation

Whitepaper called HardEval: An Execution-Verified Benchmark For AI-Driven Security Hardening And Compliance Remediation...

QuasiLeak-Bench: Evaluating LLM-Based Privacy Detectors on Policy-Conditioned Quasi-Evidence Group Recovery

Natural language messages often contain quasi-identifiers that are weak in isolation but can jointly reveal an individual's private attributes. We call such a jointly revealing set of cues a quasi-evidence group. Existing privacy benchmarks focus on explicit identifiers, attribute inference, or...

INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems

LLM-based agents increasingly execute long-horizon, end-to-end workflows involving shell commands, code modification, dependency installation, and interaction with remote services. This growing autonomy expands their exposure to indirect prompt injection IPI, where adversarial instructions embedd...

CyberArena: Benchmarking AI Agents in Live Symmetric Attack-And-Defense Combat

AI agents are demonstrating increasingly strong offensive and defensive cybersecurity capabilities in the real world. Current benchmarks mostly evaluate agents in isolation against static targets. Real cyber operations, however, are dynamic and coupled: security postures constantly change as...

ProtoArena: Can AI Agents Discover and Exploit Real-World Cross-Component Protocol Vulnerabilities?

Large language model LLM agents are increasingly used for vulnerability analysis, yet existing benchmarks provide limited coverage of exploitation that depends on interactions among network protocol components. Such vulnerabilities arise from inconsistencies in message interpretation, timing,...

VulnBump: A Benchmark for Fixing Vulnerable Dependencies in Real Projects While Keeping the Build and Tests Green

Software composition analysis SCA tools report far more vulnerable dependencies than teams fix: in Snyk Open Source production data, 94% of vulnerability findings have a known fixed version, yet only about 10% are resolved. Agentic coding tools could close this gap, but no benchmark evaluates the...

BrowseSafe++: Benchmarking Prompt Injection Detection across Web Contexts, Languages, and Browser Views

Browser agents need to make decisions and execute actions on behalf of users while consuming untrusted webpages, creating opportunities for malicious instructions embedded in webpages to redirect legitimate tasks. We introduce BrowseSafe++, which extends BrowseSafe from 14,719 pages to 38,675 pai...

terraform-aws-secure-baseline

terraform-aws-secure-baseline Terraform Module Registry Un módulo de Terraform para configurar tu cuenta de AWS con una línea base de seguridad razonablemente segura. La mayoría de las configuraciones se basan en CIS Amazon Web Services Foundations v1.4.0 y AWS Foundational Security Best Practice...

docker-bench-security

Docker Bench for Security Docker Bench for Security es un script que verifica docenas de buenas prácticas comunes en torno al despliegue de contenedores Docker en producción. Todas las pruebas están automatizadas y se basan en el CIS Docker Benchmark v1.6.0. Lo ponemos a disposición como una...

windows_hardening

HardeningKitty e Windows Hardening Introduzione Il progetto è nato come una semplice lista di hardening per Windows 10. Dopo qualche tempo, è stato creato HardeningKitty per semplificare l'hardening di Windows. Ora, HardeningKitty supporta le linee guida di Microsoft, CIS Benchmarks, DoD STIG e B...

APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces

Professional agents increasingly work through command-line interfaces and multiple tools over shared workspaces containing files, messages, and business applications. These environments create safety risks that are difficult to capture with attacks placed at a single, known read location. We...

agenticmem (>=0.1.4.1, <=0.1.5.0), biomni-bridge (>=0.3.1, <=0.3.3) +27 more potentially affected by CVE-2026-106443 via weasyprint (66.0.0)

weasyprint PYPI version 66.0.0 is affected by a known vulnerability. The following packages have a transitive dependency on weasyprint and may be impacted: - agenticmem =0.1.4.1, =0.3.1, =1.0.1, =0.1.2, =2025.1.0b3, =2026.3.0b2, =1.2.15, =2025.1.0b3, =1.0.3, =0.1.0, =1.59.6rc0, =1.67.6 and more...

[SECURITY] Fedora 45 Update: ocaml-benchmark-1.7-10.fc45

Benchmark provides functions to measure and compare the run-time of functions. It is inspired by the Perl module of the same name...

RAG-PIBench: A Leakage-Aware Benchmark for Prompt-Injection Detection in Trustworthy RAG Systems

Retrieval-Augmented Generation RAG systems are vulnerable to prompt-injection attacks embedded in retrieved content. We introduce RAG-PIBench, a benchmark for RAG-style prompt-injection detection containing 4,876 contextual examples across frozen train, validation, and protected-test splits. Usin...

Towards a Unified Misuse Monitoring Benchmark

LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request is split into innocuous sub-requests, and prompt injection attacks, where a compromised tool delivers a malicious instruction. Existing evaluation...

ANT: A Multi-Granularity Network Traffic Dataset and Benchmark for Agents Behavior Auditing

The growing adoption of large language model LLM agents creates a need for network administrators and security teams to audit agent behavior within organizational networks without inspecting private user content. Network traffic offers an observable source of evidence, but how much it reveals abo...

COPEX: Benchmarking LLM Robustness to Adversarial Context across Model Context Protocol Layers

Large language models increasingly mediate tool use in Model Context Protocol MCP systems, where adversarial influence may enter through user instructions, tool schemas, tool outputs, or protocol messages. Existing benchmarks often evaluate deployed agents, conflating model susceptibility with...

GO-2026-6505 vulnerabilities

Vulnerabilities for packages: llm-d-router, seaweedfs-operator, azuredisk-csi-fips, kcp, crossplane-provider-gcp-beta-networksecurity-fips, neuvector-scanner-fips, cadence, juicefs, flux-image-reflector-controller-fips, grpcurl, krakend-fips, kubernetes-csi-driver-nfs-fips, argo-workflows,...

KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards

LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existing evaluations focus on knowledge-based assessments or end-to-end agentic tasks, and do not directly measure LLMs' ability to generate executable...

Do Defenses against LLM Extraction Work across Attacks? A Lifecycle Benchmark of Black-Box Model Extraction

Large language models LLMs deployed through text-only APIs face model extraction risks, as adversaries can collect their responses to train surrogates that reproduce their capabilities. While prior work has developed diverse attacks and defenses, evaluations remain fragmented across access...