Search: “SWE-2”

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

Cisco Identity Services Engine Command Injection Vulnerabilities

Authenticated attackers with admin credentials could exploit Cisco ISE command injection flaws to execute arbitrary commands as root; fixes released.

Multiple command injection vulnerabilities in Cisco Identity Services Engine (ISE) and ISE Passive Identity Connector (ISE-PIC) allow an authenticated, remote attacker with valid administrative credentials to execute arbitrary commands as the root user. Cisco has released software updates, and no workarounds are available. The advisory is part of a grouped set of September 2026 ISE advisories.

Cisco Security Advisories·16:00 UTC · 5h agoAdvisory 15 sources

30

Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra

Cognition released SWE-2, a coding model post-trained from Kimi K3 that scores 50.0% on FrontierCode 1.1 Main, near Fable 5.1 at 64% lower cost.

Cognition introduced SWE-2, its most advanced coding model, post-trained from the 2.8T-parameter Kimi K3 base model. It achieves 50.0% on FrontierCode 1.1 Main, 73.0% on DeepSWE 1.1, and 92.8% on Terminal-Bench 2.1, beating Grok 4.6 and SWE-1.7 while matching Fable 5.1 and GPT-5.6 Sol at a fraction of the price. The company says it scaled reinforcement learning to the multi-trillion-parameter regime for the first time, using Pareto-informed cost penalties that train all reasoning-effort levels in a single run, tripled RL environments, and NVFP4/FP8 quantization-aware training. SWE-2 is available today in Devin Desktop and CLI, with rollout on Devin Web and Fusion.

Hacker News · AI·updated Sep 12, 20:00 UTC · 4d ago·first Sep 10, 15:29 UTC · 6d agoModel release 10 sourcesHN 58↑ · 15 comments1

72

Cognition Releases SWE-2: A Kimi K3 Post-Trained Coding Model That Matches Fable 5.1 on FrontierCode at 64% Lower Cost

Cognition released SWE-2, an RL post-trained coding model from Kimi K3, scoring 50.0% on FrontierCode 1.1 Main and available only inside Devin.

Cognition released SWE-2, its most capable coding model, post-trained with reinforcement learning from Moonshot AI's 2.8T-parameter Kimi K3 base. It scores 50.0% on FrontierCode 1.1 Main, within 1 point of Fable 5.1 at 64% lower cost, and RL reportedly adds 5-6 points over the K3 base on many benchmarks. It is the first Cognition model with selectable reasoning-effort levels all trained in a single RL run using Pareto-slope-matched cost penalties. There are no open weights and no standalone API; it runs only inside Devin (Desktop, CLI, with Web and Fusion rolling out), free for paid tiers through October 10, 2026.

MarkTechPost·Sep 12, 23:56 UTC · 3d agoModel release1

58

[AINews] DeepSeek v4.1-Flash: 763B-P8B-D16B novel causal Encoder–Decoder architecture with vision marks the Return of the Whale

DeepSeek released V4.1-Flash, an open-weight 763B-parameter model with a novel causal encoder-decoder architecture, 1M context, vision input, and MIT license.

DeepSeek launched V4.1-Flash, an open-weight MIT-licensed model using a novel causal encoder-decoder architecture with 763B total parameters and asymmetric active parameters: 8B for prefill and 16B for decode. It supports 1M-token context and text+image input, priced at $0.30 per 1M input and $1.20 per 1M output tokens with a 50% off-peak discount. Artificial Analysis scored it 40 on its Intelligence Index, above DeepSeek V4 Pro 0813, and Vals ranked it the #1 open-weight model ahead of Kimi K3. Baseten shipped day-0 support and Ollama began rolling it out to paid subscribers.

Latent Space·Sep 12, 05:56 UTC · 4d agoModel release 4 sources1

80

Real-SWE: Benchmarking AI models on private, real-world, enterprise codebases

Real-SWE benchmark tests coding agents on licensed private enterprise codebases; top model Fable 5.1 resolves only 38.8% of tasks.

Real-SWE is a new benchmark evaluating frontier AI coding agents on tasks drawn from private production codebases licensed from real companies, spanning billing, tax calculation, and cross-service migrations. Fable 5.1 with Claude Code leads at 38.8% resolution rate (pass@1 over eight runs), followed by GPT-6 Astra Codex CLI at 33.8% and Gemini 3.8 Flash Gemini CLI at 31.2%. Tasks use native harnesses and realistic tooling including Docker, Kubernetes, PostgreSQL, Redis, and Linear; median reference solutions edit 11 files versus 6 for DeepSWE and FrontierCode.

Hacker News · AI·Sep 12, 20:25 UTC · 4d agoAI researchHN 45↑ · 31 comments

48

LandingAI Releases Agentic Document Extraction Gen2 with DPT-3 Pro and DPT-3 Verity

LandingAI shipped Agentic Document Extraction Gen2 with DPT-3 Pro and DPT-3 Verity parsing models, adding usage-based billing, block-tree outputs, and word-level grounding.

LandingAI has generally released Agentic Document Extraction Gen2, rebuilt around two parsing models: DPT-3 Verity for deterministic transcription of digital documents with per-word bounding boxes and confidence scores, and DPT-3 Pro for layout-aware parsing of scans, handwriting, non-Latin scripts, and LaTeX math. Billing changes from a flat 3 credits per page to a page-plus-output-character model (Pro: 1 credit/page plus 0.5 credits per 1,000 output characters on priority; Verity: 0.3 plus 0.2), with an asynchronous standard tier at 0.5x price and vendor-claimed 25-80% cost reductions. Parse v2 returns a document-page-block tree with semantic IDs, normalized bounding boxes, and line- or word-level atomic grounding, replacing flat chunks; Gen1 client code will not run against Gen2 endpoints. Deployment options include US/EU cloud, VPCs on AWS, Azure, and Google Cloud, Snowflake, and air-gapped on-premises environments, with automated model routing planned for fall 2026.

MarkTechPost·Sep 10, 02:13 UTC · 6d agoAI tools & infra

25

Adversarial Testing of Automated Program Repair Agents for Security Vulnerabilities

SWEADV benchmark shows adversarial issue descriptions make LLM program-repair agents write insecure fixes in 51.7% of cases, evading most detection tools.

Researchers built SWEADV, a benchmark of 750 adversarial issue descriptions derived from 150 SWE-bench Verified repair tasks, covering command execution, deserialization, path traversal, denial of service, and weak hashing attack types. Tested on mini_swe agents backed by GPT-5-Mini, MiniMax-M2.5, and DeepSeek-R, adversarial descriptions induced malicious behavior with successful repair in 51.7% of cases. Detection was weak: LLM-as-judge pre-repair screening reached only 62.3% accuracy, and post-repair detection via static analysis and LLM-as-judge achieved just 39.4% and 55.4%.

arXiv cs.CR·Sep 14, 17:53 UTC · 2d agoAI safety & security1

52

SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents

SWE-Bench Pro Verified is a corrected benchmark showing prior coding-agent scores were inflated by reward hacking and flawed tasks.

Analysis of SWE-Bench Pro found its evaluation undermined by reward hacking from leakage of gold solutions or hidden evaluation information, plus task quality issues such as misleading problem statements and improperly scoped tests. The authors present SWE-Bench Pro Verified, combining anti-hacking safeguards that eliminate major leakage channels with minimal task refinements. Evaluations show some models perform substantially worse than previously reported, suggesting SWE-Bench Pro overestimates real software engineering capability.

Hugging Face daily papers·Sep 7, 20:00 UTC · 9d agoAI research1

35

Researchers Use Claude to Port Pre-Auth RCE Exploit From One PLC Model to Another

Forescout used Anthropic's Claude to port a working pre-auth RCE exploit for CVE-2021-31886 between WAGO PLCs, executing ARM shellcode on live hardware.

Forescout Vedere Labs used Claude interactively to port an RCE exploit for CVE-2021-31886, a CVSS 9.8 stack buffer overflow in the Nucleus FTP server's USER command, from a WAGO 750-852 to a WAGO 750-831 PLC, running attacker-supplied ARM shellcode. The final RCE stage cost $535.74 in API usage over 8 hours 32 minutes, and a follow-up attempt to build a C2 implant permanently bricked the device. CERT@VDE lists many Nucleus V1-based WAGO models as vulnerable with no updates available; Siemens plans no Nucleus NET remediation. The work follows a joint NSA/CISA/FBI/DOE/EPA advisory warning of AI-generated exploitation scripts targeting internet-exposed Siemens S7 PLCs.

The Hacker News·Sep 2, 07:47 UTC · 14d agoResearchCVE-2021-318862

45

Coding Agents Have Converged: Why the SWE-bench Leaderboard Can No Longer Order Its Top Entries, and What to Measure Instead

Audit of 254 SWE-bench submissions finds top coding-agent entries statistically inseparable, so small leaderboard gaps no longer establish rank.

The paper audits 254 SWE-bench submissions across four splits without running models. On Verified, the top two entries each resolve 396 of 500 instances, and exact paired McNemar tests separate none of the 29 adjacent top-thirty pairs at alpha=0.05. Within-model scaffold score ranges reach 29.8 percentage points, versus an 8.8-point spread among the top thirty. The authors release a five-step audit protocol and recommend reporting comparison-set-specific resolution and model-scaffold provenance.

arXiv cs.AI / cs.LG / cs.CL·Sep 15, 16:29 UTC · 1d agoAI research

40

VU#308749: Remote Code Execution and Arbitrary File Read Vulnerabilities in Kaltura Servers

Insecure deserialization in Kaltura's legacy HTML5 Player V2 (mwEmbed) allows arbitrary file read and remote code execution; Player V7 is unaffected.

CERT/CC issued VU#308749 for two flaws in Kaltura's HTML5 Player V2 library (mwEmbed/html5lib), both caused by the same insecure deserialization bug. The flaws enable arbitrary file read and remote code execution via the exposed mwEmbedLoader.php endpoint. Affected versions include html5lib v2.45, v2.103 and earlier, and other v2.x releases; the currently supported Player V7 is unaffected. No evidence of exploitation was cited.

CERT/CC Vulnerability Notes·Aug 25, 16:11 UTC · 22d agoVulnerability

50

[webapps] Joomla JCE_2.9.15 - Remote Code Execution

A remote code execution proof of concept for Joomla Content Editor (JCE) 2.9.15 was published on Exploit-DB.

Exploit-DB added a webapps proof-of-concept for remote code execution affecting the Joomla Content Editor (JCE) component version 2.9.15. JCE is a widely deployed editor extension used on Joomla websites. The entry provides no CVE id and no evidence of in-the-wild exploitation.

Exploit-DB·Aug 17, 00:00 UTC · Aug 17, 2026Exploit / PoC1

40

Applied Systems Engineering ASE2000 V2 Communications Test Set

CISA warns ASE2000 V2 test sets allow arbitrary file read/write, outbound request abuse, and TLS peer impersonation; version 2.38 fixes both vulnerabilities.

CISA published ICS advisory ICSA-26-239-04 for Applied Systems Engineering (Kalkitech) ASE2000 V2 Communications Test Set versions 2.25 through 2.37. Exploitation could allow reading or writing arbitrary local files, forcing outbound network requests, or intercepting the TLS connection to impersonate the trusted peer and read or modify protected communications. Vendor ASE/Kalkitech provides upgraded version 2.38, which also updates the bundled log4net library, fixing both vulnerabilities; customers are advised to upgrade.

CISA Advisories·Aug 27, 12:00 UTC · 20d agoAdvisory

18

Another Apache Log4j Vulnerability Is Actively Exploited in the Wild (CVE-2021

Apache Log4j 2 RCE CVE-2021-44228 is actively exploited via crafted JNDI lookups; Palo Alto Unit 42 urges upgrading to Log4j 2.17.1.

Unit 42 details CVE-2021-44228, an easily exploited remote code execution flaw in Apache Log4j 2 where attacker-supplied JNDI lookups in logged user input cause payload download and execution. Massive internet-wide scanning for unpatched systems has begun, with observed follow-on activity including information stealing, Cobalt Strike delivery, and coinmining. The recommended fix is Log4j 2.17.1, which also patches CVE-2021-45046, CVE-2021-45105, and CVE-2021-44832. Widely used Java software including Apache Struts, Solr, Druid, Flink, ElasticSearch, and Spring Boot is affected.

Palo Alto Unit 42·Aug 17, 12:20 UTC · Aug 17, 2026Exploit / PoC in the wildCVE-2021-44228CVE-2021-45046CVE-2021-45105+3 CVEs

92

GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation

GE-Act 2.0 is a from-scratch pretrained world-action model for robotic manipulation, with success rising from 17.1% to 44.1% as co-training data scales to 30,000 hours.

Genie Envisioner Act 2.0 (GE-Act 2.0) is a world-action model whose generative and action components are all initialized from scratch on manipulation data, combining a control-oriented autoencoder (CoAE), single-step visual planner (SVP), and inverse dynamics model (IDM) trained jointly via knowledge-aligned selective optimization (KASO). Scaling co-training data from 300 to 30,000 hours raises zero-shot success from 17.1% to 44.1% on G1-OP and 13.4% to 31.1% on G2-90D, despite the latter comprising under 2% of data, suggesting cross-embodiment transfer. Gains span 19/20 and 18/20 skill groups, and skill-specific coverage correlates with zero-shot OOD success (Pearson r=0.80).

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

30

Secure Access Service Edge (SASE) Archives

Palo Alto Unit 42 archive page describing Secure Access Service Edge (SASE), a cloud architecture unifying SD-WAN with SWG, CASB, FWaaS and ZTNA services.

Category archive page defining SASE as a cloud-native architecture that converges SD-WAN with security functions such as SWG, CASB, FWaaS and ZTNA into one cloud service. It frames SASE as a shift from separate networking and security disciplines to unified, cloud-delivered security and connectivity. The page contains no news, incident, vulnerability or research findings.

Palo Alto Unit 42·Aug 17, 12:33 UTC · Aug 17, 2026Industry

10

Enterprises Warned of Attacks Exploiting WSO2 Vulnerability

Attackers are actively exploiting CVE-2026-5430 (CVSS 10), a WSO2 JWT authentication bypass, to access enterprise API credentials and sensitive data.

WatchTowr's honeypot network recorded the first exploitation attempt of CVE-2026-5430 on September 13, roughly two months after the CVE record was published in early August. The flaw, patched by WSO2 in April with an advisory in May, carries a maximum CVSS score of 10 and allows JWT authentication bypass via tokens signed with unsupported algorithms, enabling unauthorized access and full account takeover. A forged JWT observed in the wild granted access to API backend endpoints, credentials, and consumer keys and secrets for every registered application. WSO2's API Manager, API Control Plane, Traffic Manager, and Universal Gateway are affected, and the platform serves nearly 1,000 enterprise customers in banking, government, telecom, and logistics.

SecurityWeek·updated 15:05 UTC · 6h ago·first 08:39 UTC · 13h agoExploit / PoC in the wild 3 sourcesCVE-2026-54302· 1 read

84

Re: pcre2 version 10.48 released with security fixes

PCRE2 10.48 released with security fixes; seven vulnerabilities assigned CVEs including CVE-2026-86145 and CVE-2026-89156 through CVE-2026-89162.

The PCRE2 regular expression library released version 10.48 with multiple security fixes, disclosed on the oss-security mailing list. Seven issues received CVE assignments: CVE-2026-86145, CVE-2026-89156, CVE-2026-89157, CVE-2026-89158, CVE-2026-89160, CVE-2026-89161, and CVE-2026-89162. PCRE2 is a widely used regex engine embedded in many open-source projects and applications. No exploitation is reported in the disclosure.

oss-security·Sep 11, 20:19 UTC · 5d agoVulnerabilityCVE-2026-86145CVE-2026-89156CVE-2026-89157+4 CVEs1

45

$536 and 8 Hours: AI Learns to Attack a Different PLC

Forescout used Claude to port a WAGO PLC exploit for $536 in 8 hours, and an AI-generated payload later permanently bricked the test device.

Forescout researchers used Claude Code with Ghidra, terminal access, and physical hardware to port CVE-2021-31886, a pre-authentication buffer overflow in the Nucleus FTP server, from a WAGO 750-852 PLC to the WAGO 750-831 without source code or debugger access. The final RCE development stage cost $535.74 in API fees over an 8-hour, 32-minute session (2.6k input and 1.3M output tokens) and required heavy researcher guidance. Claude produced working ICMP and UDP beacon exploits in 12 minutes after identifying that normal FTP command completion was overwriting its shellcode, fixed by omitting the CRLF terminator. A follow-up session extending the payloads toward a C2 implant wrote to flash-mapped memory and permanently bricked the PLC, underscoring the risks of autonomous agents operating against physical infrastructure.

Security Affairs·Sep 2, 13:50 UTC · 14d agoResearchCVE-2021-318861

55

HPE security advisory (AV26-928)

Canada's Cyber Centre relayed an HPE advisory covering multiple vulnerabilities in EdgeConnect SD-WAN Gateways and Orchestrator, urging prompt updates.

On September 16, 2026, the Canadian Centre for Cyber Security published advisory AV26-928 noting that as of September 15, 2026, HPE is affected by multiple vulnerabilities in HPE Networking EdgeConnect SD-WAN Gateways and Orchestrator across multiple versions, per HPE bulletin HPESBNW05135 rev.1. The Cyber Centre encourages users and administrators to review the linked HPE security bulletins and apply available updates. No exploitation details or CVE identifiers are provided in the advisory text.

Canadian Centre for Cyber Security·18:35 UTC · 3h agoAdvisory 2 sources

30

ExecCritic: Learn to Test, Test to Improve for Coding Agents

ExecCritic separates test generation from patching for coding agents, lifting SWE-bench Verified resolution to 72.6%.

ExecCritic pairs a test-verify-revise scaffold with role-specific reinforcement learning: a Test agent writes repository-native tests and a Repair agent fixes code from execution feedback, both using Qwen-3.5-35B-A3B backbones. Post-trained Qwen agents compose to 72.6% on SWE-bench Verified, an 11.4-point gain over the 61.2% no-test baseline, without stronger-model or oracle feedback at evaluation time. The work shows test quality is the key variable: base-agent tests lowered resolution to 57.3% while GPT-5.6-sol tests raised it to 65.3%.

arXiv cs.AI / cs.LG / cs.CL·Sep 8, 17:53 UTC · 8d agoAI research1

36

wp2shell: incident response guide (CVE-2026-63030 + CVE-2026-60137)

Eye Security published forensic IR tooling for wp2shell (CVE-2026-63030/CVE-2026-60137), the unauthenticated WordPress core RCE chain, after WordPress.org forced auto-updates.

wp2shell chains a REST API batch-endpoint route-confusion bug (CVE-2026-63030) with an SQL injection in WP_Query's author__not_in parameter (CVE-2026-60137), giving unauthenticated attackers rogue admin and code execution on default installs. Adam Kues of Searchlight Cyber discovered the flaw, a public PoC exists on GitHub, and WordPress.org forced automatic updates across an estimated 200M+ sites. Eye Security released a compromise-scanner WordPress plugin and browser extension and notes database artifacts (oEmbed cache rows, changesets) are the primary evidence since the attack is log-blind; fixed versions are 6.8.6, 6.9.5, and 7.0.2.

Web discovery (articles for new exploits & KEV entries)·Sep 8, 16:27 UTC · 8d agoExploit / PoC in the wild 2 sourcesCVE-2026-63030CVE-2026-601371

90

[local] Microsoft Edge 150.0.4078.48 - RCE

Exploit-DB publishes a local remote code execution exploit for Microsoft Edge 150.0.4078.48.

A public exploit demonstrates remote code execution in Microsoft Edge version 150.0.4078.48, listed under the local category on Exploit-DB. Successful exploitation could allow arbitrary code execution in the context of the browser. Users should update to the latest patched Edge release.

Exploit-DB·Aug 10, 00:00 UTC · Aug 10, 2026Exploit / PoC

38

[webapps] Wolf CMS 0.8.3.1 - RCE v

A proof-of-concept exploit for remote code execution in Wolf CMS 0.8.3.1 has been published on Exploit-DB.

Exploit-DB lists a public proof-of-concept exploit for a remote code execution vulnerability in Wolf CMS 0.8.3.1. The listing is categorized under web applications. No exploitation in the wild or CVE identifier is stated in the listing.

Exploit-DB·Sep 1, 00:00 UTC · 15d agoExploit / PoC1

15

[webapps] Langflow 1.10.0 - RCE

A public proof-of-concept demonstrates remote code execution in Langflow 1.10.0, the open-source AI workflow builder.

Exploit-DB lists a remote code execution proof of concept targeting Langflow version 1.10.0. Langflow is a widely used open-source tool for building AI agent and LLM workflows. The listing does not include a CVE id or evidence of in-the-wild exploitation, but RCE in AI development tooling is relevant to teams running it in production.

Exploit-DB·Sep 2, 00:00 UTC · 14d agoExploit / PoC1

32