LLM-Assisted Detection and Repair of Hardware Security Vulnerabilities in Verilog Designs

Hardware designs, like software, are susceptible to bugs that can introduce security vulnerabilities and create opportunities for malicious exploitation. Unlike software vulnerabilities, however, hardware flaws become permanently embedded in silicon after fabrication, making them difficult or...

Hardware Design and Security in the Era of Chiplets and LLMs

The semiconductor industry is undergoing a dual revolution: the shift toward heterogeneous 2.5D chiplet systems and the integration of Large Language Models LLMs into Electronic Design Automation EDA flows. While these paradigms offer unprecedented benefits in yield, modularity, design...

LiteLLM 1.83.6 Blind SQL Injection

A proof of concept exploit for a pre-authentication blind SQL injection vulnerability in LiteLLM version 1.83.6. The vulnerability affects LiteLLM proxy versions 1.81.16 through 1.83.6 and occurs because the virtual-key lookup interpolates an unauthenticated bearer token directly into a PostgreSQ...

Flyto2 Core: LLM/API keys leak to an attacker-controlled base_url

Summaryllm.chat reads the operator's provider key from the environment OPENAIAPIKEY, ANTHROPICAPIKEY, ... and sends it in the Authorization: Bearer header to baseurl, a parameter the caller controls. baseurl is only checked against the SSRF guard, and the guard allows any public host, so pointing...

AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection

Prompt injection remains a critical threat to LLM agents, yet existing defenses treat each task as a self-contained problem, independent of previous encounters. In practice, user requests are often underspecified: they describe the desired outcome without fully specifying acceptable behavior. An...

Post-Hoc Trajectory-Risk Certification for Modular LLM-Based Security Agents

Autonomous security agents operate as staged pipelines, such as classifying network traffic and then attributing attacks to a specific technique. Split conformal prediction gives each stage finite-sample coverage, but deployment requires a trajectory-level guarantee across the full chain. These...

A Security-Oriented Lifecycle Model for Large Language Model Systems

Large language models are being integrated into critical infrastructure and enterprise workflows at unprecedented scale,yet the lifecycle frameworks governing their development and operations were designed for operational efficiency rather than security analysis. As a result, security-relevant...

MalTotal: Cost-Effective and Language-Agnostic Malicious Code Poisoning Detection for Millions of Repositories

The widespread adoption of open source software OSS has introduced significant security risks, with malicious code poisoning attacks increasingly targeting public package registries and open-source platforms. Existing detection approaches, including heuristic-, learning-, and LLM-based methods,...

CVE-2026-67598

Emlog Pro through 2.6.23 contains a disabled TLS certificate validation vulnerability in include/service/ai.php that allows network-adjacent attackers to intercept outbound HTTPS requests to configured LLM providers by presenting arbitrary TLS certificates, as CURLOPTSSLVERIFYPEER and...

EUVD-2026-52405

Emlog Pro through 2.6.23 contains a disabled TLS certificate validation vulnerability in include/service/ai.php that allows network-adjacent attackers to intercept outbound HTTPS requests to configured LLM providers by presenting arbitrary TLS certificates, as CURLOPTSSLVERIFYPEER and...

TrainShield: Targeted Awareness for Cybersecurity Training

In recent years, cybersecurity threats have increasingly exploited human behaviour rather than purely technical vulnerabilities, exposing the limits of traditional awareness programmes delivered outside real-world contexts. To bridge this gap, we introduce TrainShield, an interaction paradigm for...

enot-autodl (>=3.3.1, <=3.4.3), farm-haystack (1.5.0) +6 more potentially affected by CVE-2026-9856 via transformers (4.19.2)

transformers PYPI version 4.19.2 is affected by a known vulnerability. The following packages have a transitive dependency on transformers and may be impacted: - enot-autodl =3.3.1, =0.7.2, =0.2.0, =2.1.0, =2.1.2 - textdiversity 0.0.1 Source cves: CVE-2026-9856 Source advisory:...

Why Formal Monitors Fail: Attack Distribution Entropy As a Coverage Bound for LTL-Based LLM Agent Safety

Runtime safety monitors based on Linear Temporal Logic LTL and finite automata FSA are increasingly deployed to intercept unsafe tool-call sequences in LLM agents. Yet the same monitor achieves 68-75% attack coverage on some model architectures and near-zero on others, with no explanation from...

From Chasing Ghosts to Missed Attacks: Perspectives and Perceptions of SOC Practitioners on LLM Integration, Risks, and Readiness

Security Operations Centers SOCs process large volumes of security events, requiring analysts to accurately detect and assess ongoing cyberattacks under time pressure. Recent advances in Large Language Models LLMs suggest potential benefits for security operations, yet their practical suitability...

Symbolic Attack Chain Generation from Atomic Red Team Techniques: An Empirical Study of Predicate Representation Granularity

Automated attack chain generation is critical for modern cybersecurity, yet manual construction fails to scale as adversary behaviors expand. While classical AI planning using PDDL offers a formal method to automate this process, it relies on the accurate translation of techniques into symbolic...

Hidden prompt can make Microsoft Copilot spread itself through your Word docs

A security researcher has demonstrated how Microsoft Copilot for Word can be tricked into spreading a self‑propagating prompt‑injection “AI worm.” The attack silently alters documents and embeds its own hidden instructions into newly created files, allowing it to spread through normal...

Hidden prompt turns Microsoft Copilot into an AI worm

A security researcher has demonstrated how Microsoft Copilot for Word can be tricked into spreading a self‑propagating prompt‑injection “AI worm.” The attack silently alters documents and embeds its own hidden instructions into newly created files, allowing it to spread through normal...

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist. A malicious instruction crafted by an attacker may be stored in long-term memory, recalled much later, and quietly shape a real action. Recent benchmarks increasing...

Xalgorix Autonomous AI Pentesting Agent 4.5.89

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents

Software engineering teams now deploy AI coding agents Cursor, Claude Code, GitHub Copilot as first-class productivity tools, installing domain-specific skill files to tailor agent behavior to project APIs, framework conventions, and organizational workflows. These complex Markdown files are easi...