ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents

As large language model LLM agents move from conversation to executing code, reading local files, and orchestrating external tools, a single agent hijacked by a malicious third-party skill can cause data exfiltration, privilege escalation, or cascading compromise. We argue that agentic risk is...

PT-2026-79364

Headroom's LLM proxy lets a client choose the upstream destination with the x-headroom-base-url request header. resolve openai upstream base in headroom/proxy/handlers/openai.py accepts the header value, requires only that it parse with an http or https scheme and a hostname, and returns it for u...

CVE-2026-77775: Server-Side Request Forgery (SSRF)

Headroom's LLM proxy lets a client choose the upstream destination with the x-headroom-base-url request header. resolveopenaiupstreambase in headroom/proxy/handlers/openai.py accepts the header value, requires only that it parse with an http or https scheme and a hostname, and returns it for use ...

CVE-2026-77776: Authorization Bypass Through User-Controlled Key

Headroom's LLM proxy derives the memory owner from the x-headroom-user-id request header. The header is read directly at several points in headroom/proxy/handlers/openai.py, including the chat completion and websocket paths, and nothing binds the value to the caller. A client can therefore name...

TraceGrant: A Contract-Governed Security Framework for the Task-Effect Lifecycle of Networked LLM Agents

Networked large language model LLM agents retrieve information from email, cloud storage, calendars, transaction platforms, and Web services to complete multistep tasks that produce persistent external effects. The same content needed for legitimate execution may also contain indirect prompt...

PT-2026-79365

Headroom's LLM proxy derives the memory owner from the x-headroom-user-id request header. The header is read directly at several points in headroom/proxy/handlers/openai.py, including the chat completion and websocket paths, and nothing binds the value to the caller. A client can therefore name...

Vibe Coding and Web Application Security: A Twin-Prompt Study

Large language models increasingly generate complete web applications from natural-language prompts, raising the question of whether explicitly requesting security best practice improves the result. We study six functionally distinct web applications, each generated in two prompt variants that ar...

Enhancing User Resilience against AI-Augmented Phishing: A Two-Stage Framework for Detection and Personalized Training

The rapid development of artificial intelligence, including agents and deepfake techniques, has accelerated phishing attacks and lowered the threshold for attackers. Modern phishing attacks now blend multiple tactics, including social engineering, URL spoofing, and AI deepfakes enabling adversari...

vulnerability-harness

Vulnerability Harness An LLM harness that reads code, for...

xalgorix v4.5.153

Xalgorix — Open-source AI pentester that proves vulnerabilities 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...

Structural Inference in Undocumented Mobile Databases: A Reproducible Benchmark for Evaluating Agentic Reasoning in Digital Forensics

Agentic large language models are increasingly used in digital forensic analysis, yet their ability to infer relational structure inside undocumented mobile application databases remains poorly understood. In forensic contexts, structurally incorrect inferences can yield results that appear...

Beyond End-To-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents

Long-horizon security LLM agents must carry information and decisions across many dependent interactions, where later actions often depend on services, state, or access discovered much earlier. This makes final task success difficult to interpret: an agent may fail before it ever reaches the poin...

AEGIS: Preventing Cross-Domain Resource Abuse in MCP

The Model Context Protocol MCP is an open source JSON-RPC protocol that standardizes how large language models LLMs interact with external systems through programmatic functions known as tools. Attackers or malicious agents can exploit certain modalities of these MCP tools to degrade the overall...

The Claws in Plain Sight: Unauthorized Context Disclosure through LLM Agent Tool Calls

LLM agents routinely construct tool-call arguments from user profiles, conversation history, retrieved documents, and prior tool results. However, legitimate access to contextual information does not imply authorization to transmit that information for every purpose or destination. We present Cla...

AiXamine: Unified Black-Box Evaluation of Cross-Dimensional Trade-Offs in LLM Safety, Security, and Privacy

The critical failure modes in deployed large language models LLMs are cross-dimensional: a model can score 99.3 in safety alignment while refusing one in three benign queries, or improve across every capability metric while losing 21 points in privacy. Existing evaluation frameworks that assess...

MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection

Agent Skills extend LLM agents with reusable instruction packages that may also include scripts, resources, and service configuration. This creates a direct distribution channel for malicious behavior, yet existing malicious-Skill datasets are fragmented across sources, artifact formats, evidence...

From Noise to Signal: Improving Security Log Anomaly Detection Using LLMs with Endpoint-Specific Logs

Existing approaches to anomalous behaviour log detection, such as Wazuh rely primarily on predefined detection rules, while statistical anomaly detection approaches such as OpenSearch identify deviations from previously observed behavioural patterns. Recent research has investigated LLMs for log...

Contentful MCP Server: export_space/import_space tools pass LLM-controlled `host`/`proxy` args to CMA client, redirecting server PAT to attacker-controlled endpoint

Summary exportspace and importspace tools in @contentful/mcp-tools accept LLM-controlled host and proxy parameters that are spread directly into the options object passed to contentful-export / contentful-import. These libraries pass the merged options — including the attacker-controlled host — t...

Project-Ronin

Project Ronin Documentation Hub Welcome to the technical doc...

Scrapegraph-ai v2.1.7

🚀 Looking for an even faster and simpler way to scrape at scale only 5 lines of code? Check out our enhanced version at ScrapeGraphAI.com! 🚀 🕷️ ScrapeGraphAI: You Only Scrape Once English | 中文 | 日本語 | 한국어 | Русский | Türkçe | Deutsch | Español | français | Português | Italiano ScrapeGraphAI is a...