Semantic Denial of Service in LLM-Controlled Robots

Safety-oriented instruction-following is supposed to keep LLM-controlled robots safe. We show it also creates an availability attack surface. By injecting short safety-plausible phrases 1-5 tokens into a robots audio channel, an adversary can trigger the models safety reasoning to halt or disrupt...

Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents

Autonomous Large Language Model LLM agents are increasingly deployed to conduct complex tasks by interacting with external tools, APIs, and memory stores. However, processing untrusted external data exposes these agents to severe security threats, such as indirect prompt injection and unauthorize...

Mitigate or Fail: How Risk Management Shapes Cybersecurity Competency

Contemporary cybersecurity governance assumes that professionals apply risk reasoning. Yet major organisational failures persist despite investment in tools, staffing, and credentials. This study investigates the structural source of that paradox. Cybersecurity speaks the language of risk, but it...

EUVD-2025-209538

Cross-Site Scripting XSS vulnerability reflected in Semantic MediaWiki. This vulnerability allows an attacker to execute JavaScript code in the victim's browser by sending them a malicious URL using the '/index.php/Speciaal:GefacetteerdZoeken' endpoint parameter. This vulnerability can be exploit...

CVE-2025-10354

Cross-Site Scripting XSS vulnerability reflected in Semantic MediaWiki. This vulnerability allows an attacker to execute JavaScript code in the victim's browser by sending them a malicious URL using the '/index.php/Speciaal:GefacetteerdZoeken' endpoint parameter. This vulnerability can be exploit...

CVE-2025-10354

CVE-2025-10354 describes a reflected Cross-Site Scripting (XSS) vulnerability in Semantic MediaWiki. The vulnerability allows an attacker to cause JavaScript execution in a victim’s browser by sending them a crafted URL that abuses the /index.php/Speciaal:GefacetteerdZoeken parameter. Impact per ...

CVE-2025-10354

Cross-Site Scripting XSS vulnerability reflected in Semantic MediaWiki. This vulnerability allows an attacker to execute JavaScript code in the victim's browser by sending them a malicious URL using the '/index.php/Speciaal:GefacetteerdZoeken' endpoint parameter. This vulnerability can be exploit...

CVE-2025-10354 Reflected Cross-Site Scripting (XSS) in Semantic MediaWiki

Cross-Site Scripting XSS vulnerability reflected in Semantic MediaWiki. This vulnerability allows an attacker to execute JavaScript code in the victim's browser by sending them a malicious URL using the '/index.php/Speciaal:GefacetteerdZoeken' endpoint parameter. This vulnerability can be exploit...

CVE-2025-10354 Reflected Cross-Site Scripting (XSS) in Semantic MediaWiki

Cross-Site Scripting XSS vulnerability reflected in Semantic MediaWiki. This vulnerability allows an attacker to execute JavaScript code in the victim's browser by sending them a malicious URL using the '/index.php/Speciaal:GefacetteerdZoeken' endpoint parameter. This vulnerability can be exploit...

Semantic MediaWiki 跨站脚本漏洞

Semantic MediaWiki is an open-source extension of Semantic MediaWiki that stores and queries data within wiki pages. Semantic MediaWiki has a cross-site scripting vulnerability. This vulnerability stems from the endpoint parameters in /index.php/Speciaal:GefacetteerdZoeken, which allow for...

PT-2026-33973

Cross-Site Scripting XSS vulnerability reflected in Semantic MediaWiki. This vulnerability allows an attacker to execute JavaScript code in the victim's browser by sending them a malicious URL using the '/index.php/Speciaal:GefacetteerdZoeken' endpoint parameter. This vulnerability can be exploit...

Owner-Harm: A Missing Threat Model for AI Agent Safety

Existing AI agent safety benchmarks focus on generic criminal harm cybercrime, harassment, weapon synthesis, leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own deployers. Real-world incidents illustrate the gap: Slack AI...

CodeQL 2.25.2

Discover vulnerabilities across a codebase with CodeQL, an industry-leading semantic code analysis engine. CodeQL lets you query code as though it were data. Write a query to find all variants of a vulnerability, eradicating it forever. Then share your query to help others do the same...

Security Is Relative: Training-Free Vulnerability Detection Via Multi-Agent Behavioral Contract Synthesis

Deep learning for vulnerability detection has shown promising results on early benchmarks, but recent evaluations reveal catastrophic degradation: models achieving F1 0.68 on legacy datasets collapse to 0.031 under strict deduplication. We identify the root cause as the semantic ambiguity problem...

SDLLMFuzz: Dynamic-Static LLM-Assisted Greybox Fuzzing for Structured Input Programs

Fuzzing has become a widely adopted technique for vulnerability discovery, yet it remains ineffective for structured-input programs due to strict syntactic constraints and limited semantic awareness. Traditional greybox fuzzers rely on mutation-based strategies and coarse-grained coverage feedbac...

K000160730: Microsoft semantic kernel Python SDK vulnerability CVE-2026-26030

Security Advisory Description Semantic Kernel, Microsoft's semantic kernel Python SDK, has a remote code execution vulnerability in versions prior to 1.39.4, specifically within the InMemoryVectorStore filter functionality. The problem has been fixed in version python-1.39.4. Users should upgrade...

Security Bulletin: Vulnerabilities in hoek, Bouncy Castle Inc, Spring Framework, golang, Apache Commons, semver and Google Guava might affect IBM Storage Defender Copy Data Management

Summary IBM Storage Defender Copy Data Management can be affected by vulnerabilities in hoek, Bouncy Castle Inc, Spring Framework, golang, Apache Commons, semver and Google Guava. Vulnerabilities include allowing a malicious user to modify the prototype of "Object" via proto, causing the addition...

Beyond Single Reports: Evaluating Automated ATT&CK Technique Extraction in Multi-Report Campaign Settings

Large-scale cyberattacks, referred to as campaigns, are documented across multiple CTI reports from diverse sources, with some providing a high-level overview of attack techniques and others providing technical details. Extracting attack techniques from reports is essential for organizations to...

ARuleCon: Agentic Security Rule Conversion

Security Information and Event Management SIEM systems make it possible for detecting intrusion anomalies in real-time manner by their applied security rules. However, the heterogeneity of vendor-specific rules e.g., Splunk SPL, Microsoft KQL, IBM AQL, Google YARA-L, and RSA ESA makes...

Your LLM Agent Can Leak Your Data: Data Exfiltration Via Backdoored Tool Use

Tool-use large language model LLM agents are increasingly deployed to support sensitive workflows, relying on tool calls for retrieval, external API access, and session memory management. While prior research has examined various threats, the risk of systematic data exfiltration by backdoored...