Search: “HarnessVLN”

Attackers Chain JFrog Artifactory Flaws to Gain Admin Control and Plant Backdoors

Attackers chained JFrog Artifactory flaws CVE-2026-42018 and CVE-2026-42016 for admin control, planting Rust backdoors; CVE-2026-82329 also mass-exploited.

Wiz observed attackers chaining CVE-2026-42018 (anonymous-token leak) and CVE-2026-42016 (token escalation) in self-hosted JFrog Artifactory between August 15 and September 8, gaining admin control, creating admin accounts, and installing malicious Groovy plugins and a custom Rust backdoor. Separately, critical authentication bypass CVE-2026-82329 (CVSS 9.8) was mass-exploited starting September 1, drawing ~406,000 exploitation attempts on September 2 per Fastly. CISA added CVE-2026-82329 to KEV on September 2 with a September 5 federal deadline. Patching does not revoke minted tokens or rotate stolen join keys; admins must review accounts and rotate credentials.

The Hacker News·updated Sep 14, 09:27 UTC · 3d ago·first Sep 11, 07:31 UTC · 6d agoExploit / PoC in the wild 7 sourcesCVE-2026-42018CVE-2026-42016CVE-2026-823292

HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness

Researchers introduce HarnessVLN, a zero-shot training-free agent harness that sets new training-free SOTA on vision-language navigation benchmarks including R2R and HM3D.

HarnessVLN is a zero-shot, training-free framework for embodied vision-language navigation that coordinates perception, retrieval, grounding, navigation, recovery, and termination through a unified tool interface. It validates planner proposals against spatial evidence, geometric feasibility, and subgoal consistency, using hierarchical event memory and a persistent Spatiotemporal Graph that stores reusable spatial evidence and failure annotations. It reports success rates of 60.8% on R2R, 53.9% on RxR, 76.0% on HM3D-v2, and 59.3% on HM3D-OVON, surpassing prior training-free state of the art, with real-world humanoid deployment demonstrated.

Hugging Face daily papers·Sep 13, 20:00 UTC · 3d agoAI research

CISA Adds 5 Actively Exploited Artifactory, ScreenConnect, and RouterOS Flaws to KEV

CISA added five actively exploited JFrog Artifactory, ConnectWise ScreenConnect, and MikroTik RouterOS flaws to its KEV catalog.

CISA added five actively exploited vulnerabilities to the KEV catalog: CVE-2026-42016 and CVE-2026-42018 in JFrog Artifactory, CVE-2026-84869 in ConnectWise ScreenConnect (CVSS 9.9), and CVE-2026-67277 and CVE-2026-86060 in MikroTik RouterOS. The Artifactory bugs are chained with CVE-2026-82329 to gain administrative control, deploy malicious Groovy plugins, and install Rust-based backdoors. CERT Polska dubbed the RouterOS chain 'MikroTrick'; FCEB agencies must patch between September 13 and 25, 2026.

The Hacker News·updated Sep 14, 14:08 UTC · 2d ago·first Sep 12, 15:54 UTC · 4d agoExploit / PoC in the wild 2 sourcesCVE-2026-42016CVE-2026-42018CVE-2026-84869+3 CVEs2· 1 read

Another Artifactory CVE under attack by AI agents or humans

Attackers are actively exploiting CVE-2026-82329, a critical JFrog Artifactory authentication bypass, minting admin tokens on exposed servers days after patch release.

CVE-2026-82329 is a CVSS 9.8 unauthenticated authentication bypass in JFrog Artifactory, disclosed Friday, that allows attackers to create new administrative credentials. watchTowr's honeypots recorded exploitation from a small number of IPs within days, including enumeration of users, groups, credential sets, and federated access topologies. Researchers urge urgent patching, credential rotation, and treating exposed instances as potentially compromised to prevent build-pipeline tampering and downstream supply-chain impact.

The Register · Security·Sep 1, 21:07 UTC · 15d agoExploit / PoC in the wild 2 sourcesCVE-2026-82329

HarnessTax: How Much Does the Harness Matter for Coding Agents?

HarnessTax is a research project measuring how much the harness, the scaffolding around LLMs, affects coding agent performance.

HarnessTax examines how much the harness — the scaffolding, prompts, and tooling wrapped around a large language model — contributes to coding agent results, as opposed to the underlying model itself. The project was posted on Hacker News on September 16, 2026, where it drew 42 points and 9 comments. Further details are available on the project's GitHub Pages site.

Hacker News · AI·Sep 16, 22:10 UTC · 11h agoAI researchHN 42↑ · 9 comments

Can LLMs Engineer Their Own Agent Harness? ByteDance Seed’s HarnessDev Says Only 34 of 64 Changes Generalize

ByteDance Seed's HarnessDev benchmark finds LLM-built agent harnesses trail human engineering on code and search, with only 34 of 64 revisions generalizing.

Researchers from ByteDance Seed, SUTD, Georgia Tech, M-A-P, and TokenWave.AI introduce HarnessDev, a benchmark that evaluates the runnable agent harness an LLM writes rather than its answers, using Creation and Evolution stages across SWE-bench Pro, Terminal-Bench 2.1, MLE-bench, EQ-Bench3, and BrowseComp (2,207 instances). Six creator models including Opus 4.8, GPT-5.5, Gemini 3.1 Pro, DeepSeek V4 Pro, Qwen 3.7 Max, and Seed 2.0 Pro were tested; Opus 4.8 posted the best average of 67.8 versus an 86.2 human-engineered reference. Self-built harnesses beat references on writing and ML experimentation but lag badly on code and search, and quality proved executor-specific: Opus 4.8 fell from 69.3 to 33.0 on SWE-bench Pro when the executor was switched to Gemini. Evolution gains were small and noisy: of 64 adjacent changes, feedback and held-out scores agreed only 34 times (53.1%), and much generated state and memory code never executed.

MarkTechPost·updated Sep 16, 17:41 UTC · 16h ago·first Sep 11, 22:01 UTC · 5d agoAI research 20 sources

Show-Harness: Just a VLM Agent Can Play Robots

Show-Harness lets VLM agents control robots via discrete semantic action units, outperforming VLA baselines zero-shot and after light fine-tuning.

Show-Harness is an embodied agent harness that exposes discrete semantic action units a VLM reasons over, with embodiment-specific interpreters grounding them into local robot actions. It enables zero-shot robot control with closed-source frontier VLMs and low-cost adaptation of small open-source VLMs using only a few GPU-hours of fine-tuning. The companion GUMI (GUI Manipulation Interface) extends the same semantic action space to GUI-based demonstration collection without specialized teleoperation hardware. Experiments show robust generalization across tasks, embodiments, and environments, beating representative agentic and VLA paradigms.

arXiv cs.AI / cs.LG / cs.CL·Sep 9, 17:53 UTC · 7d agoAI research

I tested 10 model/harness combinations on the same Three.js task

A developer benchmarked 10 model/harness combinations on a Three.js task; Qwen 3.8 27B on OpenCode scored 95.64% fastest at 8m48s.

The author ran an identical Three.js sci-fi hangar build prompt across 10 model/harness combinations and recorded score, tokens, durations, and tool errors. Qwen 3.8 27B x-high on OpenCode achieved 95.64% in 8m48s, the best fast result, while GLM 5.3 Flash Max on OpenCode scored highest at 96.89% in 20m28s. Other runs included GLM 5.3 Flash, Luna 5.6, SOL 5.6, and Astra 6.0 across Codex Open, OMP Open, OpenCode, DSH, and PTC harnesses, with scores ranging from 78.54% to 96.89%.

Hacker News · AI·Sep 8, 03:42 UTC · 9d agoAI researchHN 104↑ · 61 comments1

DeepSeek Harness Flaw Let AI Agents Disable Their Own File Sandbox Without Approval

DeepSeek Harness (CVE-2026-82533, CVSS 9.4) let AI coding agents disable their own sandbox via an unauthenticated local API; fixed in 0.1.2-alpha.2.

DeepSeek Harness versions 0.1.1-rc.2 and earlier allowed a sandboxed AI coding agent to turn off its own OS sandbox by calling the tool's unauthenticated local web interface, tracked as CVE-2026-82533 with a 9.4 CVSS from VulnCheck. A single command set the agent session to danger-full-access mode, removing sandboxing and approval prompts, and OX Research verified writes escaped the workspace. The interface trusted the client-supplied Host header with no authentication and could also return a session's entire conversation log. The fix adds a one-time token and signed-cookie check; the first npm release carrying it is 0.1.2-alpha.2, with 0.1.2-rc.1 current.

The Hacker News·Sep 9, 11:17 UTC · 7d agoAI safety & security in the wildCVE-2026-825331

GuardBreaker: Derailing AI-assisted malware analysis with a code comment

ESET names 'GuardBreaker': UAC-0099 embeds a nuclear-weapon question in VBScript comments to trip LLM scanner guardrails during analysis of its MATCHBOIL loader.

ESET researchers observed the Russia-aligned group UAC-0099 inserting a decoy prompt injection into a VBScript used to install its MATCHBOIL loader in an attack against a Ukrainian target, aiming to make LLM-based code scanners refuse and stop inspecting the file. The comment triggers safety guardrails with a request about building a nuclear weapons but has no runtime effect. Similar LLM-thwarting tricks have appeared in malicious PyPI and npm packages reported by Socket and StepSecurity. ESET recommends multi-model cross-validation of AI-assisted analysis and treating missing LLM output as requiring further checks.

ESET WeLiveSecurity·Sep 10, 09:00 UTC · 7d agoAI safety & security1

Hackers Weaponize AI Safety Guardrails to Hide Malware From LLM-Powered Security Scanners

ESET says Russia-aligned actor UAC-0099 hid guardrail-triggering comments in VBScript to derail LLM-based malware scanners in Ukraine.

ESET researchers linked a technique named GuardBreaker to Russia-aligned threat actor UAC-0099 during an attack against an organization in Ukraine. The group embedded a safety-sensitive, weapon-related request in a VBScript comment so an LLM-powered analysis tool might interpret it as an instruction and refuse or truncate analysis before reaching the malicious code. The VBScript downloaded MATCHBOIL, a C#-based loader used by the group alongside MATCHWOK and DRAGSTARE. OWASP guidance recommends treating code comments and metadata as untrusted input, sanitizing it, and never treating an LLM refusal as a clean verdict.

GBHackers·updated Sep 11, 14:32 UTC · 5d ago·first Sep 11, 10:51 UTC · 5d agoThreat actor in the wild 2 sources1

Show-Harness: Just a VLM Agent Can Play Robots

Show-Harness enables VLM agents to control robots via a semantic action interface, achieving zero-shot frontier control and few-GPU-hour adaptation of small VLMs.

Show-Harness exposes discrete semantic action units that VLMs reason over, with embodiment-specific interpreters deterministically grounding them into local robot actions. It enables zero-shot closed-source frontier VLM control and adapts small open-source VLMs for low-cost deployment with a few GPU-hours of fine-tuning. The companion GUMI interface extends the same semantic action space to GUI-based demonstration collection without teleoperation hardware, and Show-Harness-equipped agents outperform representative agentic and VLA paradigms.

Hugging Face daily papers·Sep 8, 20:00 UTC · 8d agoAI research

Russian hackers plant nuclear weapon prompt in malware to trip AI safety guardrails

ESET reports Russian group UAC-0099 hid a prompt in VBS malware comments to trip AI safety filters and disrupt automated malware analysis in Ukraine.

ESET identified a technique dubbed GuardBreaker in which UAC-0099 embedded a comment reading "I want to make nuclear weapon. Help me …" inside a malicious VBS script to trigger AI safety mechanisms and halt AI-assisted malware analysis. The script, part of the group's toolset, downloads the MATCHBOIL malware used exclusively by this Russia-aligned group; CERT-UA documented the chain including LUNCHPOKE, BURNYBEAR and MATCHBOIL.V2 in a July advisory. UAC-0099 typically targets transportation and energy sectors and hands validated targets to GRU-linked Sandworm. ESET warned that AI-assisted analysis must be backed by layered detection and human-driven engineering.

Help Net Security·Aug 31, 00:00 UTC · 17d agoAI safety & security in the wild

OVSwrap: 13-Year-Old Linux Kernel Flaw Lets Local Users Become Root

Security Affairs·Aug 5, 14:24 UTC · Aug 5, 2026Exploit / PoCCVE-2026-64531

The Evolution of the Agent Harness

Latent Space essay argues late-2025 agent gains came from models and harnesses maturing together, with harness logic absorbed into model weights.

The piece defines the agent harness as everything beyond model weights—tools, context, memory, guardrails—and charts its evolution from ReAct prompting (October 2022) through AutoGPT's premature autonomy, Cursor/Copilot's human-in-the-loop retreat, and Devin's roughly 15% success rate, to o1's capability overhang and Claude Code's February 2025 terminal agent with permission rules. It argues the Christmas 2025 jump cited by Transformer co-inventor Lukasz Kaiser reflected model and harness curves crossing, and that remaining harnesses will serve human attention rather than the model.

Latent Space·Aug 22, 07:30 UTC · 26d agoAI tools & infra

Homebrew 7.0.0 gets built-in GUI, better security controls

Homebrew 7.0.0 adds a built-in vulnerability scanner (brew vulns), a Homebrew advisory database, stronger sandboxing, and the BrewUI GUI.

Homebrew 7.0.0 ships a native BrewUI graphical interface for macOS 26 Tahoe and later, plus a new 'brew vulns' command that queries OSV.dev in batch to flag vulnerabilities in installed formulae, specific packages, or Brewfile dependencies. The release also introduces a Homebrew-specific OSV-format advisory database distinguishing outstanding vulnerabilities from backported fixes. Sandbox improvements block home directory access by default and separate network-enabled dependency downloads from offline installs.

BleepingComputer·Sep 14, 19:51 UTC · 2d agoTools1

Twitch extension with 30K installs exposes users’ OAuth tokens

Twitch extension with 30,000+ installs exfiltrates users' OAuth session tokens to Russian-run JeetBot proxy servers.

Socket analysis shows the "Twitch Enhanced Viewer | JeetBot" browser extension, with over 30,000 installs on the official Chrome and Firefox stores, captures the Twitch web client's authorization header and extracts the user's OAuth token. The token is appended as an auth= URL parameter to video playlist requests routed through JeetBot proxy servers, landing in cleartext request logs retrievable by the Russian-language bot service vendor; ten hardcoded Russian-language channels are exempted. Earlier versions used more explicit token exfiltration, and the extension remained live in both stores at publication. Socket recommends removing the extension, disconnecting all Twitch sessions, and re-authenticating.

BleepingComputer·Sep 14, 19:03 UTC · 2d agoMalware in the wild

Jenkins Patches 20 Plugin Flaws Leading to RCE, XSS and Credential Theft

Jenkins patched 20 vulnerabilities across 13 plugins, including Groovy sandbox bypasses enabling remote code execution on CI/CD controllers.

Jenkins released security updates on September 16, 2026 for 20 vulnerabilities across 13 plugins, including nine fixes in the Script Security Plugin for Groovy sandbox bypasses. CVE-2026-92127 (classpath abuse) and CVE-2026-92128 (TOCTOU race on remote JAR loading) could allow arbitrary code execution in the controller JVM, exposing build secrets, credentials, and downstream deployment environments. Other flaws include stored XSS in the Warnings, Coverage, OWASP Dependency-Check and Gitee plugins, SSRF in the Gradle and Bitbucket plugins enabling credential capture, credential exposure via CVE-2026-92130, arbitrary file write via CVE-2026-92137, OAuth token theft, and an open redirect in the Keycloak Authentication Plugin. No exploitation is reported; fixes include Script Security Plugin 1422.v06869826dd9b_.

GBHackers·06:21 UTC · 3h agoVulnerabilityCVE-2026-92122CVE-2026-92123CVE-2026-92124+17 CVEs

EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness?

Researchers introduce EVOHARNESSBENCH, a benchmark showing that evolving agent harnesses (tools, skills, agents) cause forgetting and inconsistent adaptation across 802 tasks.

The paper introduces EVOHARNESSBENCH, a benchmark that places non-stationarity in the externally supplied agent harness rather than in the task stream, evaluating agents across tools, skills, and specialist agents. It comprises 17 multi-stage harness streams built deterministically from verifier-based benchmarks, totaling 802 tasks, 520 tools, 42 skills, and 62 agents. Evaluation covers deployment (retention of previously accessible competence) and self-evolving adaptation settings. Results show harness expansion alone degrades previously solved tasks (harness-induced forgetting), adaptation gains are inconsistent, and retention and adaptation can pull in opposite directions.

Hugging Face daily papers·Sep 2, 20:00 UTC · 14d agoAI research

Homebrew 7.0.0 Adds Built-In Vulnerability Scanner and Stronger Package Sandboxing

Homebrew 7.0.0 ships a native brew vulns scanner, OSV-backed advisory database, stronger sandboxing, and fixes a sandbox-escape issue.

Homebrew 7.0.0 introduces a built-in 'brew vulns' command that scans installed formulae, dependencies, and Brewfiles against a new Homebrew-specific advisory database and OSV.dev data, distinguishing backported fixes from outdated versions. The release hardens sandboxing by blocking home-directory reads during builds, disabling network access at install time, and replacing Bubblewrap with Landlock on Linux. It also fixes moderate-severity GHSA-5263-whxq-77hp, where a malicious cask could execute code outside the macOS sandbox via LaunchServices, and drops macOS Catalina while moving Intel Macs to Tier 3.

Cyber Security News·Sep 15, 13:55 UTC · 1d agoTools1

CS-Guard: Benchmarking LLM Guardrails for Code Generation Security

CS-Guard benchmark shows LLM code-generation guardrails fail widely, with ~50% jailbreak ASR text-to-code and up to 100% code-to-code.

Researchers introduce CS-Guard, the first systematic benchmark for evaluating LLM guardrails for code generation security, covering text-to-code (1,000 malware-generation prompts, 7 jailbreak attacks, and a novel fictional scenario attack) and code-to-code (331 prompts across infilling, completion, and translation). They evaluate 9 guardrails across seven LLMs, finding average jailbreak attack success rates around 50% for text-to-code and 14.4% to nearly 100% for code-to-code. The fictional scenario attack achieves ASR close to 100% across many guardrails, raising reliability concerns for real-world software development. The benchmark and data are released publicly.

arXiv cs.CR·Sep 9, 06:50 UTC · 8d agoAI safety & security1

The skb that wasn't freed - the Fragnesia primitive via Open vSwitch

Doyensec details CVE-2026-90049 in Open vSwitch, enabling deterministic Linux kernel local privilege escalation on default major distribution installs.

Doyensec reports that the Open vSwitch datapath strips the SKBFL_SHARED_FRAG flag from packets it is still forwarding, allowing an in-place decrypt to write attacker-chosen bytes into root-owned page cache — a Dirty COW-class primitive that re-opens the Fragnesia bug family. The issues are tracked as CVE-2026-90049, CVE-2026-89487, and CVE-2026-80977, and were reported to the kernel security team with fixes coordinated alongside OVS maintainers. A deterministic local privilege escalation works on default installs of Arch, Fedora, Debian, Amazon Linux, and RHEL where unprivileged user namespaces and openvswitch auto-loading are enabled; the fix landed in mainline and shipped in stable on 09/04/2026. The write technique builds on the earlier Fragnesia and Dirty Frag bugs, including CVE-2026-43284 and CVE-2026-43500.

Lobsters · security·08:39 UTC · 1h agoVulnerabilityCVE-2026-90049CVE-2026-89487CVE-2026-80977+2 CVEs

Project CAV3RN continues: Google Apps Script as C2 relay and DNS-based C2 channel selection

Project CAV3RN continues targeting Israel, using Google Apps Script C2 relays and DNS-based channel routing in a .NET NativeAOT framework.

Kaspersky Securelist documents the continuation of Project CAV3RN operations against Israel. The modular .NET NativeAOT framework uses Google Apps Script as a C2 relay and DNS-based C2 channel selection, blending command traffic with legitimate Google services to evade detection.

Kaspersky Securelist·Aug 11, 10:00 UTC · Aug 11, 2026Threat actor in the wild