Judge-Jury-and-Executable

Judge Jury and Executable A Threat Hunting Forensics Tool Features: Scan a mounted filesystem for threats right away Or gather a system baseline before an incident, for extra threat hunting ability Can be used before, during or after an incident For one to many workstations Scans the MFT, bypassi...

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:...

ai-pentest-agent

ai-pentest-agent A small, standalone autonomous pentest agent, plus a purpose-built vulnerable target to run it against. Built to show, end to end, how an AI pentesting agent actually works — not a black box, just a plan→act→judge loop, a handful of generic skills, a gate that vetoes destructive...

Rubrics-as-an-Attack-Surface

Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges 📊 Dataset • 🤖 Trained Models • 📝 Paper • 💻 Repo This repository contains code for the paper Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges by Ruomeng Ding, Yifei Pang, He Sun, Yizhong Wang, Steven Wu, and...

Scope-Gap Injection: Exploiting Evaluator Channel Blind Spots in the OpenClaw Agent Security Competition

This paper introduces Scope-Gap Injection SGI, an indirect prompt injection method for multi-stage LLM-agent safety pipelines. In the IJCAI 2026 OpenClaw Agent Security Attack Competition, each attack package is judged by a static skill scan S1, an LLM-judge safety check over the task and skill...

Can Agentic Code Review Catch Vulnerabilities Before They Are Merged?

LLM agents have been increasingly adopted for security-focused code review, but existing benchmarks mostly derive the reviewed changes from their later fixes instead of the real-world bug-introducing commits. In this paper, we present SecPRBench, the first comprehensive benchmark for evaluating...

cellmerge (>=0.1.0, <=0.1.1), jupyter-quant (2606.1.0) +5 more potentially affected by CVE-2026-102832 via jupyterlab (>=4.6.0, <=4.6.2)

jupyterlab PYPI version =4.6.0, =0.1.0, =1.2.0, =0.1.0, =0.1.1 - tiatoolbox 2.1.3 Source cves: CVE-2026-102832 Source advisory: GHSA-JWRC-GM9J-263P...

cellmerge (>=0.1.0, <=0.1.1), jupyter-quant (2606.1.0) +5 more potentially affected by CVE-2026-102832 via jupyterlab (>=4.6.0, <=4.6.2)

jupyterlab PYPI version =4.6.0, =0.1.0, =1.2.0, =0.1.0, =0.1.1 - tiatoolbox 2.1.3 Source cves: CVE-2026-102832 Source advisory: OSV:GHSA-JWRC-GM9J-263P...

From Detection to Decision: Calibration and Deferral for Prompt-Injection Detection

Prompt-injection defenses are commonly evaluated as binary detectors, although deployed LLM applications must make operational decisions about whether to allow, block, or escalate potentially malicious inputs. Recent probabilistic decision models aim to support such decisions through calibrated...

StableJudge: A Lightweight Adversarial Defense Framework for LLM-As-A-Judge

Large language models LLMs are increasingly used as judges to assign scalar scores that drive downstream decision-making, including tasks such as paper review and recommendation. However, LLM-as-a-Judge pipelines are vulnerable to score-hijacking prompt injection embedded in evaluated content,...

cellmerge (>=0.1.0, <=0.1.1), jupyter-quant (2606.1.0) +5 more potentially affected by CVE-2026-102830 via jupyterlab (>=4.6.0, <=4.6.2)

jupyterlab PYPI version =4.6.0, =0.1.0, =1.2.0, =0.1.0, =0.1.1 - tiatoolbox 2.1.3 Source cves: CVE-2026-102830 Source advisory: OSV:PYSEC-2026-4056...

cellmerge (>=0.1.0, <=0.1.1), jupyter-quant (2606.1.0) +5 more potentially affected by CVE-2026-102831 via jupyterlab (>=4.6.0, <=4.6.2)

jupyterlab PYPI version =4.6.0, =0.1.0, =1.2.0, =0.1.0, =0.1.1 - tiatoolbox 2.1.3 Source cves: CVE-2026-102831 Source advisory: OSV:PYSEC-2026-4057...

cellmerge (>=0.1.0, <=0.1.1), jupyter-quant (2606.1.0) +5 more potentially affected by CVE-2026-102830 via jupyterlab (>=4.6.0, <=4.6.2)

jupyterlab PYPI version =4.6.0, =0.1.0, =1.2.0, =0.1.0, =0.1.1 - tiatoolbox 2.1.3 Source cves: CVE-2026-102830 Source advisory: GHSA-3JQQ-PW4J-PQCJ...

cellmerge (>=0.1.0, <=0.1.1), jupyter-quant (2606.1.0) +5 more potentially affected by CVE-2026-102904 via jupyterlab (>=4.6.0, <=4.6.2)

jupyterlab PYPI version =4.6.0, =0.1.0, =1.2.0, =0.1.0, =0.1.1 - tiatoolbox 2.1.3 Source cves: CVE-2026-102904 Source advisory: GHSA-3325-V43H-43RV...

cellmerge (>=0.1.0, <=0.1.1), jupyter-quant (2606.1.0) +5 more potentially affected by CVE-2026-102831 via jupyterlab (>=4.6.0, <=4.6.2)

jupyterlab PYPI version =4.6.0, =0.1.0, =1.2.0, =0.1.0, =0.1.1 - tiatoolbox 2.1.3 Source cves: CVE-2026-102831 Source advisory: GHSA-6966-VJJ6-99XV...

cellmerge (>=0.1.0, <=0.1.1), jupyter-quant (2606.1.0) +5 more potentially affected by CVE-2026-102904 via jupyterlab (>=4.6.0, <=4.6.2)

jupyterlab PYPI version =4.6.0, =0.1.0, =1.2.0, =0.1.0, =0.1.1 - tiatoolbox 2.1.3 Source cves: CVE-2026-102904 Source advisory: SNYK:PYTHON-JUPYTERLAB-20335547...

cellmerge (>=0.1.0, <=0.1.1), jupyter-quant (2606.1.0) +5 more potentially affected by CVE-2026-102904 via jupyterlab (>=4.6.0, <=4.6.2)

jupyterlab PYPI version =4.6.0, =0.1.0, =1.2.0, =0.1.0, =0.1.1 - tiatoolbox 2.1.3 Source cves: CVE-2026-102904 Source advisory: MEND:CVE-2026-102904...

cellmerge (>=0.1.0, <=0.1.1), jupyter-quant (2606.1.0) +5 more potentially affected by CVE-2026-102831 via jupyterlab (>=4.6.0, <=4.6.2)

jupyterlab PYPI version =4.6.0, =0.1.0, =1.2.0, =0.1.0, =0.1.1 - tiatoolbox 2.1.3 Source cves: CVE-2026-102831 Source advisory: MEND:CVE-2026-102831...

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...