1121 matches found
Malicious code in winston-elara-semantic-release-tethys (npm)
The package winston-elara-semantic-release-tethys was found to contain malicious code...
MAL-2025-44822 Malicious code in json-aquarius-exoplanetology-semantic-release (npm)
The package json-aquarius-exoplanetology-semantic-release was found to contain malicious code...
MAL-2025-43677 Malicious code in bunyan-lacerta-electron-builder-semantic-ui (npm)
The package bunyan-lacerta-electron-builder-semantic-ui was found to contain malicious code...
MAL-2025-43430 Malicious code in algol-cross-env-biomimicry-semantic-ui (npm)
The package algol-cross-env-biomimicry-semantic-ui was found to contain malicious code...
MAL-2025-45995 Malicious code in semantic-release-metalsmith-mini-css-extract-plugin-framework (npm)
The package semantic-release-metalsmith-mini-css-extract-plugin-framework was found to contain malicious code...
MAL-2025-46640 Malicious code in winston-elara-semantic-release-tethys (npm)
The package winston-elara-semantic-release-tethys was found to contain malicious code...
MAL-2025-46160 Malicious code in subscription-test-semantic-ui-tailwindcss (npm)
The package subscription-test-semantic-ui-tailwindcss was found to contain malicious code...
MAL-2025-44339 Malicious code in frontend-equinox-docusaurus-semantic-release (npm)
The package frontend-equinox-docusaurus-semantic-release was found to contain malicious code...
MAL-2025-45994 Malicious code in semantic-release-dotenv-safe-commitlint-node-sass (npm)
The package semantic-release-dotenv-safe-commitlint-node-sass was found to contain malicious code...
MAL-2025-45996 Malicious code in semantic-ui-selenium-test-postcss (npm)
The package semantic-ui-selenium-test-postcss was found to contain malicious code...
MAL-2025-45253 Malicious code in mutation-nodemon-semantic-release-barnard (npm)
The package mutation-nodemon-semantic-release-barnard was found to contain malicious code...
MAL-2025-45993 Malicious code in semantic-release-aether-quantum-elara (npm)
The package semantic-release-aether-quantum-elara was found to contain malicious code...
MAL-2025-45982 Malicious code in sedimentology-semantic-release-cordelia-rehype (npm)
The package sedimentology-semantic-release-cordelia-rehype was found to contain malicious code...
Mind the Gap: Evaluating Model- and Agentic-Level Vulnerabilities in LLMs with Action Graphs
As large language models transition to agentic systems, current safety evaluation frameworks face critical gaps in assessing deployment-specific risks. We introduce AgentSeer, an observability-based evaluation framework that decomposes agentic executions into granular action and component graphs,...
NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models
In deployment and application, large language models LLMs typically undergo safety alignment to prevent illegal and unethical outputs. However, the continuous advancement of jailbreak attack techniques, designed to bypass safety mechanisms with adversarial prompts, has placed increasing pressure ...
SREC: Encrypted Semantic Super-Resolution Enhanced Communication
Semantic communication SemCom, as a typical paradigm of deep integration between artificial intelligence AI and communication technology, significantly improves communication efficiency and resource utilization efficiency. However, the security issues of SemCom are becoming increasingly prominent...
VULSOVER: Vulnerability Detection Via LLM-Driven Constraint Solving
Traditional vulnerability detection methods rely heavily on predefined rule matching, which often fails to capture vulnerabilities accurately. With the rise of large language models LLMs, leveraging their ability to understand code semantics has emerged as a promising direction for achieving more...
PromptSleuth: Detecting Prompt Injection Via Semantic Intent Invariance
Large Language Models LLMs are increasingly integrated into real-world applications, from virtual assistants to autonomous agents. However, their flexibility also introduces new attack vectors-particularly Prompt Injection PI, where adversaries manipulate model behavior through crafted inputs. As...
MultiFuzz: a Dense Retrieval-Based Multi-Agent System for Network Protocol Fuzzing
Traditional protocol fuzzing techniques, such as those employed by AFL-based systems, often lack effectiveness due to a limited semantic understanding of complex protocol grammars and rigid seed mutation strategies. Recent works, such as ChatAFL, have integrated Large Language Models LLMs to guid...