Malicious code in nebula-llm (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector b33da6aef41209f654f8f76cc56074a7b827599f42f941e3917326da1f4d2566 The npm package [email protected] ships a preinstall lifecycle script preinstall.cjs that embeds a 257KB Windows PE binary as a base64+zlib-compressed...

MAL-2026-17227 Malicious code in nebula-llm (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector b33da6aef41209f654f8f76cc56074a7b827599f42f941e3917326da1f4d2566 The npm package [email protected] ships a preinstall lifecycle script preinstall.cjs that embeds a 257KB Windows PE binary as a base64+zlib-compressed...

Malicious Package

Overview nebula-llm is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and this package authorship...

Malicious Package

Overview llm-nebula is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and this package authorship...

JEV As a Judge for Agent Trace Security: An Empirical Comparison with Generative LLM Judges

Security evaluation of tool-using agents requires judging actions in context, yet generative judges add latency, explanation overhead, and output-validation failures. We study whether JEV, a typed decision model, offers a useful alternative for retrospective trace classification. We evaluate JEV...

ReproBench: Benchmarking LLM Agents on Reproducing Vulnerability from Scratch

Large language model LLM agents are increasingly evaluated on cybersecurity tasks such as vulnerability reproduction, exploitation, and patching. However, existing cybersecurity benchmarks predominantly operate under a post-environment evaluation paradigm, i.e., handing the agent source code, a...

CoDeL: Co-Evolutionary Defense against Indirect Prompt Injection in LLM-Based Agents

Large language model LLM-based agents increasingly rely on external tools and content, exposing them to indirect prompt injection IPI. This threat has motivated a wide range of defenses, among which training-based defenses are often regarded as most reliable. However, existing training-based...

"Nothing to See Here'': Unintended Disclosure through Revision Traces of LLM Deliverables

Large language model LLM assistants increasingly help users draft content for third-party recipients. During private drafting, the user or the model may introduce an item and later remove or replace it. The model may remove the item from the intended content but reveal it again when stating the...

LLM-Assisted Automatic Security Proofs for Cryptographic Protocols: How Far Are We?

Whitepaper called LLM-Assisted Automatic Security Proofs For Cryptographic Protocols: How Far Are We?...

Trajectory-Level Security Debt in LLM Coding Agents

LLM coding agents can traverse hundreds of intermediate code states before submitting a solution. Evaluating only the final artifact leaves the evolution of security findings unmeasured. We introduce the Security Debt Line Integral SDLI, which accumulates static-analysis risk when an agent reache...

Continuous Assurance of Agentic Security Auditors for Software Delivery Decision Gates

Large language model LLM-based repository auditors are increasingly deployed as security controls within continuous integration CI pipelines, where their findings admit, block, or delay software changes. As Agentic Software Development Life Cycle SDLC Security Controls, their non-deterministic...

Know the Normal, Track the Attack: Context-Grounded and Stateful LLM Investigation over System Provenance

Provenance-based intrusion detection systems PIDSs identify suspicious activity in audit streams, but their outputs remain difficult to turn into coherent attack narratives. Direct LLM analyses of local anomalous subgraphs lack deployment-specific normal-behavior knowledge and validated attack...

PrivacySkills: How Privacy Guidance Shapes Source Selection in LLM Agents

While prior work has documented privacy failures in LLM agents, it remains unclear how the presentation of privacy guidance influences their choice of information sources. We introduce PrivacySkills, a controlled framework for evaluating how agents choose among acquisition pathways that provide t...

Inference-Layer Security: Defending against Adversarial Inference and Infrastructure Abuse

A Technical Report: Operating a large language model LLM as a service requires more than inference infrastructure: the provider must also defend against adversarial interactions that seek to exploit the service, including jailbreaking for harmful use, sophisticated denial of service, and...

Tokenized Key-Gated Adapter Routing: A Secure Access Control Mechanism against Private Data Leakage in LLMs

Large language models LLMs are increasingly deployed in privacy-critical domains e.g., healthcare, finance, and government, but their propensity to memorize and disclose personally identifiable information PII poses serious security and compliance risks. Existing defenses typically force a...

CyberPersistBench: Evaluating LLM-Based Cyber Attackers on Installation and Persistence

While LLM-based attackers exhibit growing proficiency in vulnerability exploitation, most existing cybersecurity benchmarks suffer from single-stage truncation, prematurely terminating evaluation upon initial access. In practice, initial footholds are exceptionally fragile across operational...

Separation of Duties for Privileged LLM Agents: A Governed Execution Architecture with Measured Security-Utility Trade-Offs

Large language model agents are increasingly granted real privileges executing commands, modifying files, calling APIs, so an agent that errs has already acted. Existing defences concentrate on the agent's inputs, while the path from a candidate action to privileged side effects remains less...

Similarity Is Not Validity: Defending LLM Semantic Caches against Poisoning

Semantic caches reduce LLM serving costs by reusing previously generated answers for semantically similar queries. However, retrieval is based solely on embedding similarity between the incoming query and cached queries. This design enables cache poisoning: an attacker can cache a malicious...

Same Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection

Prompt injection against LLM agents becomes much stronger when the injected instruction is wrapped in the model's own chat template. A forged template marker such as can reach the model either as a single reserved control token or as a sequence of ordinary subword tokens. The two decode to exactl...

Share-Borne AI Virus: Memory-Hopping Attacks across LLM Agents

Large language models are increasingly deployed as stateful assistants that retain information across interactions and use tools to read, modify, and create persistent artifacts. As these artifacts are shared between users, they form an indirect communication channel between otherwise independent...