MarketNow built a 6-layer audit pipeline called Sentinel that tests for 7 of the 10 OWASP MCP Top 10 risks. The pipeline uses active probes, sandboxing, dependency scanning, and weekly re-audits to de…
A developer built MarketNow, a marketplace that security-audits every MCP server before listing, after 30 CVEs were filed against MCP servers in 60 days. The audit pipeline, Sentinel, includes static …
A developer compared four MCP server marketplaces: Smithery, Glama, PulseMCP, and MarketNow. MarketNow, built by the developer, is the only one that security-audits every server, using a 6-layer pipel…
A developer built Sentinel, a six-layer audit pipeline that runs every MCP server in the MarketNow catalog. The pipeline combines static analysis, dependency scanning, behavioral pattern detection, ad…
LayerX documented BioShocking, an adversarial framing technique that tricks AI browsers and assistants into exfiltrating user credentials. The attack convinces the AI it is participating in a game, by…
An open-source benchmark for prompt-injection detectors has been released, measuring both attack catch rate and false positives on real traffic in a threshold-agnostic way. The benchmark evaluates ten…
Palo Alto Networks Unit 42 has documented real-world indirect prompt injection attacks against LLM-powered agents, where adversaries embed malicious instructions into web content that agents browse, c…
A flaw in Amazon Q Developer allowed malicious repositories to inject rogue Model Context Protocol (MCP) configurations, leading to arbitrary code execution. The vulnerability exploited the agent's tr…
Microsoft's threat intelligence team attributed a supply chain attack targeting the Mastra AI ecosystem to North Korean state-sponsored hacking group Sapphire Sleet (BlueNoroff). The attackers comprom…
AgentArk, an open-source self-hosted AI agent operating system, launched in beta by developer @debankadas. The platform provides a secure runtime for building, deploying, and monitoring AI agents, fea…
A developer built Sentinel, a local tool that scans any codebase in 55 seconds without cloud uploads or internet. It generates a ~2,500-token prompt for AI coding agents, using only Python stdlib with…
Sentinel, a new open-source tool, scans codebases of up to 25,000 files in 55 seconds to generate structured, token-efficient context packs for AI coding agents. It operates entirely offline with zero…
A vulnerability chain in LangGraph, a widely deployed agentic AI framework, exposed self-hosted deployments to remote code execution. Attackers manipulated agent tool-calling behavior through prompt i…
A new class of attack called 'Agentjacking' targets AI coding agents by manipulating their tool-execution pipeline, exploiting the observation-action loop that makes them productive. The attack inject…
Sentinel launched a live scanner that detects antidetect browsers including Kameleo, GoLogin, and Multilogin at the device layer, catching threats that bypass legacy fraud APIs from IPQS, SEON, and Si…
Sentinel launched an autonomous product management platform designed to ingest customer feedback from multiple channels, generate prioritized tickets, and draft product requirement documents. The syst…
A developer built Sentinel, a real-time fraud detection system that processes 71,000 requests per second with p95 latency under 6 milliseconds. The system handles 7.8 million requests with zero errors…
A developer has released Sentinel v0.3.0, an external security layer designed to prevent AI agents from going rogue. The tool uses a Shield Sidecar process that operates independently of the agent, bl…
A small European team developed CatyAI, an AI infrastructure platform that makes websites readable by AI crawlers like GPTBot and ClaudeBot, preventing chatbots from inventing prices and services. Goo…