Judge-Jury-and-Executable

Judge Jury and Executable एक थ्रेट हंटिंग फोरेंसिक टूल विशेषताएँ: किसी माउंटेड फाइलसिस्टम को तुरंत खतरों के लिए स्कैन करें या किसी घटना से पहले सिस्टम बेसलाइन एकत्र करें, अतिरिक्त थ्रेट हंटिंग क्षमता के लिए किसी घटना से पहले, उसके दौरान या बाद में उपयोग किया जा सकता है एक से लेकर कई वर्कस्टेशनों ...

FinRED-paper

FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming IEEE ICDM 2026 A red-team benchmark generation pipeline for safety evaluation in the financial domain. Supplementary Documentation Detailed materials referenced in the paper:...

Rubrics-as-an-Attack-Surface

المعايير كسطح هجومي: انحراف التفضيلات الخفي في حكام النماذج اللغوية الكبيرة 📊 مجموعة البيانات • 🤖 النماذج المدرَّبة • 📝 الورقة البحثية • 💻 المستودع يحتوي هذا المستودع على الكود الخاص بالورقة البحثية المعايير كسطح هجومي: انحراف التفضيلات الخفي في حكام النماذج اللغوية الكبيرة من تأليف Ruomeng Ding،...

Attack Success Rate Is Not a Number: On Measurement Validity in Agentic AI Security Evaluation

Attack success rate ASR is the headline metric in nearly every published evaluation of attacks on, and defenses for, LLM agents. We argue that ASR as currently used is not a single quantity but a family of metrics parameterized by six design choices that papers seldom specify and never hold...

CVE-2026-55617 Hydro: Insufficient session expiration when recreating sessions

Hydro is a next-generation high-performance online judge platform. From 4.10.4 until 5.0.2, the session recreation logic in packages/hydrooj/src/service/layers/base.ts creates a replacement session token without deleting the previous token from the server-side session token store, so an old sid...

exploitgym-unified

ExploitGym Unified Runner - 898 instâncias + Dashboard Live R...

Ranked by the Matcher: A Reproducibility Audit of Knowledge Graph Extraction from Threat Reports

Security teams and researchers choose knowledge-graph extraction tooling for threat reports on the strength of published triple-F1 scores, yet those scores depend on how predicted triples are matched to gold annotations. We could reimplement the stated matching rule for only five of twelve...

CLEAR: Causal Context-Based Agentic Reasoning for Vulnerability Detection

Detecting source code vulnerabilities is increasingly difficult as modern security flaws are rooted in complex causal dependencies between execution flows, control conditions, and program states. Despite recent advances in Large Language Models LLMs and multi-agent frameworks, existing approaches...

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist. A malicious instruction crafted by an attacker may be stored in long-term memory, recalled much later, and quietly shape a real action. Recent benchmarks increasing...

SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents

Software engineering teams now deploy AI coding agents Cursor, Claude Code, GitHub Copilot as first-class productivity tools, installing domain-specific skill files to tailor agent behavior to project APIs, framework conventions, and organizational workflows. These complex Markdown files are easi...

StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents

Stealth, the discipline of achieving an objective without revealing your presence, capabilities, or collected intelligence, is what separates sophisticated operators from detectable ones. Elite security researchers and advanced persistent threats achieve their objectives unnoticed; autonomous...

From Signals to Behaviors: Evidence-Based Android Malware Detection

Android malware remains a persistent threat, and detecting it accurately is a long-standing open problem. Whether an app is malicious depends on what it actually does and the context in which it does it, not on the surface signals it happens to exhibit. Existing detectors instead reason about...

ProfMalPlus: Agent-Coordinated Detection of Malicious NPM Packages Via Static-Dynamic Analysis Synergy

Open source software is vulnerable to supply-chain attacks through transitive dependencies, especially malicious code injected into NPM packages. Existing detectors often inadequately model obfuscated behavior, overlook JavaScript's object-centric features, poorly coordinate static and dynamic...

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents

Agentic red-teaming benchmarks report whether an injected agent was compromised as a single bit: the attack succeeded, or it did not. We argue that this binary attack-success rate discards the information a defender most needs, namely how harmful the resulting action was. We introduce an...

Detecting Malicious Agent Skills in the Wild Using Attention

LLM agents increasingly load skills, file-based packages of natural-language instructions written by third parties and distributed through marketplaces, that execute with the user's privileges. A single malicious skill can exfiltrate data, hijack the agent, or persist as a supply-chain foothold,...

TrustedRouter-ExploitBench

TrustedRouter-ExploitBench Notes, harness configs, and a runb...

CVE-2026-9528

A vulnerability was identified in itsourcecode Electronic Judging System 1.0. Impacted is an unknown function of the file /admin/deletejudge.php. Such manipulation of the argument judgeid leads to sql injection. The attack can be executed remotely. The exploit is publicly available and might be...

ZERO-APT: A Closed-Loop Adversarial Framework for LLM-Driven Automated Penetration Testing under Intelligent Defense

LLM-driven automated penetration testing agents are typically evaluated against static targets that neither detect nor respond to attacks, so their behavior under intelligent defense remains untested. The causal consistency of multi-step attack chains likewise hinges on unstable LLM reasoning, an...

CVE-2026-9525

A vulnerability has been found in itsourcecode Electronic Judging System 1.0. This affects an unknown part of the file /admin/editjudge.php. The manipulation of the argument judgeid leads to sql injection. The attack may be initiated remotely. The exploit has been disclosed to the public and may ...

CVE-2026-9528

A vulnerability was identified in itsourcecode Electronic Judging System 1.0. Impacted is an unknown function of the file /admin/deletejudge.php. Such manipulation of the argument judgeid leads to sql injection. The attack can be executed remotely. The exploit is publicly available and might be...