14 matches found
vulnhuntr
Ein Tool zur Identifizierung remote ausnutzbarer Schwachstellen mithilfe von LLMs und statischer Codeanalyse. Erste autonome KI-entdeckte 0-Day-Schwachstellen der Welt Beschreibung Vulnhuntr nutzt die Leistungsfähigkeit von LLMs, um automatisch vollständige Code-Aufrufketten zu erstellen und zu...
ollama-consumer
ollama-consumer App consumatore demo bloccata alla versione github.com/ollama/ollama v0.5.0 — utilizzata da Endor Labs per dimostrare il rilevamento delle vulnerabilità e l'analisi della catena di exploit contro la libreria upstream ollama...
invokeai-consumer
invokeai-consumer App consumer demo ancorata a invokeai==5.0.1 — usata da Endor Labs per dimostrare il rilevamento di vulnerabilità e l'analisi delle catene di exploit contro la libreria upstream invokeai. v5.0.1 è la versione specifica indicata nel CVE di origine CVE-2024-10821...
web3-decoder
Web3 Decoder Web3 Decoder è un'estensione per Burp Suite che aiuta ad analizzare cosa succede con le operazioni che coinvolgono smart contract del web3. Si tratta principalmente di chiamate JSON-RPC a nodi Ethereum e nodi di altre reti compatibili come Polygon, Arbitrum, BSC... Download e...
sigma-audit
Sigma Stack Audit Full-spectrum security audit combining five...
Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models
Large language models LLMs increasingly rely on explicit chain-of-thought CoT reasoning to solve complex tasks, yet the safety of the reasoning process itself remains largely unaddressed. Existing work on LLM safety focuses on content safety--detecting harmful, biased, or factually incorrect...
VOID
VOID ██╗ ██╗ ██████╗ ██╗██████╗ ██║ ██║██╔═══██╗██║█...
Security Risks of Agentic Vehicles: A Systematic Analysis of Cognitive and Cross-Layer Threats
Agentic AI is increasingly being explored and introduced in both manually driven and autonomous vehicles, leading to the notion of Agentic Vehicles AgVs, with capabilities such as memory-based personalization, goal interpretation, strategic reasoning, and tool-mediated assistance. While framework...
Decompiling Smart Contracts with a Large Language Model
The widespread lack of broad source code verification on blockchain explorers such as Etherscan, where despite 78,047,845 smart contracts deployed on Ethereum as of May 26, 2025, a mere 767,520 1% are open source, presents a severe impediment to blockchain security. This opacity necessitates the...
From Searching in the Dark to Seeing Ahead With Hive Pro’s Enhanced BAS
Running short on time but still want to stay in the know? Well, we’ve got you covered! We’ve condensed all the key takeaways into a handy audio summary. Our AI-driven podcasts are fit for on the go. Click right here to hear it all on Hive Pro's Enhanced BAS! During a recent incident response, I...
Secret White House Warrantless Surveillance Program
There seems to be no end to warrantless surveillance: According to the letter, a surveillance program now known as Data Analytical Services DAS has for more than a decade allowed federal, state, and local law enforcement agencies to mine the details of Americans’ calls, analyzing the phone record...
Sanction Bypass Through Transferring to another account
Lines of code Vulnerability details Impact Wildcat protocol provides lending with lender backed collateral considered as reserves and the ratio must be upheld by the borrower. WildcatMarketTokens are provided to lenders in return for their base assets, these tokens are ERC20 meaning tokens can be...
Target Kill Chain Analysis
Last week, I talked with Wall Street Journal reporter Ben DiPietro about the persistent communications gap between the data center and the board room when it comes to recognizing and tackling security threats: In almost every breach situation after his company completes a forensic analysis, Mr...
