Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction

LLM-based autonomous agents possess capabilities such as reasoning, tool invocation, and environment interaction, enabling the execution of complex multi-step tasks. The internal reasoning process, i.e., thought, of behavioral trajectory significantly influences tool usage and subsequent actions...

WordPress plugin Year Make Model Search for WooCommerce 跨站请求伪造漏洞

WordPress and WordPress plugin are both products of the WordPress Foundation, a blogging platform developed in PHP. The platform supports personal blog sites on PHP and MySQL servers.WordPress plugin is an application plugin. A cross-site request forgery vulnerability exists in the WordPress plug...

CVE-2025-22233

CVE-2024-38820 ensured Locale-independent, lowercase conversion for both the configured disallowedFields patterns and for request parameter names. However, there are still cases where it is possible to bypass the disallowedFields checks. Affected Spring Products and Versions Spring Framework: 6.2...

R1dacted: Investigating Local Censorship in DeepSeek'S R1 Language Model

DeepSeek recently released R1, a high-performing large language model LLM optimized for reasoning tasks. Despite its efficient training pipeline, R1 achieves competitive performance, even surpassing leading reasoning models like OpenAI's o1 on several benchmarks. However, emerging reports suggest...

Improving LLM Outputs against Jailbreak Attacks with Expert Model Integration

Using LLMs in a production environment presents security challenges that include vulnerabilities to jailbreaks and prompt injections, which can result in harmful outputs for humans or the enterprise. The challenge is amplified when working within a specific domain, as topics generally accepted fo...

CVE-2025-4834

A vulnerability was found in TOTOLINK A702R, A3002R and A3002RU 3.0.0-B20230809.1615. It has been classified as critical. Affected is an unknown function of the file /boafrm/formSetLg of the component HTTP POST Request Handler. The manipulation of the argument submit-url leads to buffer overflow...

CVE-2025-4831

A vulnerability, which was classified as critical, was found in TOTOLINK A702R, A3002R and A3002RU 3.0.0-B20230809.1615. This affects an unknown part of the file /boafrm/formSiteSurveyProfile of the component HTTP POST Request Handler. The manipulation of the argument submit-url leads to buffer...

CVE-2025-4830

A vulnerability, which was classified as critical, has been found in TOTOLINK A702R, A3002R and A3002RU 3.0.0-B20230809.1615. Affected by this issue is some unknown functionality of the file /boafrm/formSysCmd of the component HTTP POST Request Handler. The manipulation of the argument submit-url...

Self-Destructive Language Model

Harmful fine-tuning attacks pose a major threat to the security of large language models LLMs, allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment, they fail to address models' inherent "trainability" on harmfu...

The Impact of Emerging Phishing Threats: Assessing Quishing and LLM-Generated Phishing Emails against Organizations

Modern organizations are persistently targeted by phishing emails. Despite advances in detection systems and widespread employee training, attackers continue to innovate, posing ongoing threats. Two emerging vectors stand out in the current landscape: QR-code baits and LLM-enabled pretexting. Yet...

TOTOLINK A720R、TOTOLINK A3002R和TOTOLINK A3002RU 安全漏洞

TOTOLINK A3002RU and others are products of China Gion Electronics TOTOLINK.TOTOLINK A3002RU is a wireless router product.TOTOLINK A720R is a wireless router.TOTOLINK A3002R is a wireless router.TOTOLINK A3002R is a wireless router. A security vulnerability exists in the TOTOLINK A720R, TOTOLINK...

Spring Framework DataBinder Case Sensitive Match Exception

CVE-2024-38820 ensured Locale-independent, lowercase conversion for both the configured disallowedFields patterns and for request parameter names. However, there are still cases where it is possible to bypass the disallowedFields checks. Affected Spring Products and Versions Spring Framework: 6.2...

CVE-2025-22233

CVE-2024-38820 ensured Locale-independent, lowercase conversion for both the configured disallowedFields patterns and for request parameter names. However, there are still cases where it is possible to bypass the disallowedFields checks. Affected Spring Products and Versions Spring Framework: 6.2...

CVE-2025-22233

CVE-2024-38820 ensured Locale-independent, lowercase conversion for both the configured disallowedFields patterns and for request parameter names. However, there are still cases where it is possible to bypass the disallowedFields checks. Affected Spring Products and Versions Spring Framework: 6.2...

OESA-2025-1520 nodejs security update

Node.js is an open-source, cross-platform, JavaScript runtime environment, it executes JavaScript code outside of a browser. Security Fixes: A vulnerability has been identified in Node.js, affecting users of the experimental permission model when the --allow-fs-write flag is used. Node.js...

OESA-2025-1519 nodejs security update

Node.js is an open-source, cross-platform, JavaScript runtime environment, it executes JavaScript code outside of a browser. Security Fixes: A vulnerability has been identified in Node.js, affecting users of the experimental permission model when the --allow-fs-write flag is used. Node.js...

CVE-2025-4767 defog-ai introspect Test Endpoint integration_routes.py test_custom_tool code injection

A vulnerability was found in defog-ai introspect up to 0.1.4. It has been rated as critical. Affected by this issue is the function testcustomtool of the file introspect/backend/integrationroutes.py of the component Test Endpoint. The manipulation of the argument inputmodel leads to code injectio...

PYSEC-2025-145

A vulnerability in the Ollama server version 0.5.11 allows a malicious user to cause a Denial of Service DoS attack by customizing the manifest content and spoofing a service. This is due to improper validation of array index access when downloading a model via the /api/pull endpoint, which can...

CVE-2025-4753

A vulnerability was found in D-Link DI-7003GV2 24.04.18D1 R68125 and classified as problematic. Affected by this issue is some unknown functionality of the file /login.data. The manipulation leads to information disclosure. The attack may be launched remotely. The exploit has been disclosed to th...

GenoArmory: a Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models

We propose the first unified adversarial attack benchmark for Genomic Foundation Models GFMs, named GenoArmory. Unlike existing GFM benchmarks, GenoArmory offers the first comprehensive evaluation framework to systematically assess the vulnerability of GFMs to adversarial attacks. Methodologicall...