844 matches found
Refusal Evaluation in Coding LLMs and Code Agents: A Systematic Review of Thirteen Malicious-Code Prompt Corpora (2023-2025)
The evaluation of large language model refusal on malicious-coding tasks now spans at least thirteen publicly released prompt corpora AdvBench, the CyberSecEval family, RMCBench, RedCode, MCGMark, JailbreakBench, CySecBench, MalwareBench, CIRCLE, MOCHA, ASTRA, Scam2Prompt / Innoc2Scam-bench, and...
CVE-2026-44170
Disclaimer: This data contains information about vulnerable...
May 12, 2026-KB5087055 Cumulative Update for .NET Framework 4.8.1 for Windows 11, version 26H1
None None...
May 12, 2026-KB5087068 Cumulative Update for .NET Framework 3.5 and 4.8 for Windows Server 2022
None None...
KB5088064: Servicing stack update for Windows 10, version 1607 and Windows Server 2016: May 12, 2026
None None...
Skill Description Deception Attack against Task Routing in Internet of Agents
A new paradigm, Internet of Agents IoA, is transforming networked systems into LLM-driven service networks, where heterogeneous agents collaborate through task routing based on their self-declared skill descriptions. Although this promising paradigm enables agentic, distributed, and advanced...
SUSE CVE-2026-43131
In the Linux kernel, the following vulnerability has been resolved: drm/amd/pm: Fix null pointer dereference issue If SMU is disabled, during RAS initialization, there will be null pointer dereference issue here...
drm/amdgpu/ras: Move ras data alloc before bad page check
...
CVE-2026-43131
A flaw was found in the Linux kernel. When the System Management Unit SMU is disabled during Reliability, Availability, and Serviceability RAS initialization, a null pointer dereference occurs within the drm/amd/pm module. This issue can lead to a system crash, resulting in a Denial of Service Do...
CVE-2026-43131
In the Linux kernel, the following vulnerability has been resolved: drm/amd/pm: Fix null pointer dereference issue If SMU is disabled, during RAS initialization, there will be null pointer dereference issue here...
A Validated Prompt Bank for Malicious Code Generation: Separating Executable Weapons from Security Knowledge in 1,554 Consensus-Labeled Prompts
Existing benchmarks of language-model refusal on malicious-coding tasks routinely conflate requests for executable malicious software with requests for harmful security knowledge. This conflation matters because the two request types plausibly trigger distinct refusal pathways in safety-aligned...
IWCC 2026 Call for Papers
The 15th International Workshop on Cyber Crime, or IWCC, 2026 call for papers has been announced. It will be held this year in conjunction with the International Conference on Availability, Reliability and Security ARES 2026 in Link�ping, Sweden, August 24th through the 27th, 2026...
Evaluating Jailbreaking Vulnerabilities in LLMs Deployed As Assistants for Smart Grid Operations: A Benchmark against NERC Standards
The deployment of Large Language Models LLMs as assistants in electric grid operations promises to streamline compliance and decision-making but exposes new vulnerabilities to prompt-based adversarial attacks. This paper evaluates the risk of jailbreaking LLMs, i.e., circumventing safety alignmen...
Duplicate Advisory: uutils coreutils incorrectly handles exit codes when processing multiple files
Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-4x34-chg5-mwjj. This link is maintained to preserve external references. Original Description The recursive mode -R of the chmod utility in uutils coreutils incorrectly handles exit codes when processing multipl...
CVE-2026-35370
The id utility in uutils coreutils miscalculates the groups= section of its output. The implementation uses a user's real GID instead of their effective GID to compute the group list, leading to potentially divergent output compared to GNU coreutils. Because many scripts and automated processes...
Unity Linux 20.1050e / 20.1060e / 20.1070e Security Update: kernel (UTSA-2026-011150)
The Unity Linux 20 host has a package installed that is affected by a vulnerability as referenced in the UTSA-2026-011150 advisory. In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: disable sdma ecc irq only when sdma RAS is enabled in suspend sdmav40ip is shared on ...
SUSE-SU-2026:21210-1 Security update for google-cloud-sap-agent
This update for google-cloud-sap-agent fixes the following issue: Update to google-cloud-sap-agent 3.12 bsc1259816: - CVE-2026-33186: google.golang.org/grpc: authorization bypass due to improper validation of the HTTP/2: path pseudo- header bsc1260265. Changes for google-cloud-sap-agent: Collect...
Surgical Repair of Insecure Code Generation in LLMs
Large language models write production code, and yet they routinely introduce well-known vulnerabilities. We show that this is not a knowledge deficit: the same models that generate insecure code, correctly identify and explain the vulnerability when asked directly, this is a gap we call the...