SecureAI-Scan is an open-source (MIT) static analysis scanner for TypeScript, JavaScript and Python code that calls LLMs or serves MCP tools. It finds prompt injection, sensitive data in prompts and logs, unsafe handling of model output, MCP tool-argument command injection and path traversal, tool poisoning, RAG and vector-store weaknesses, and Agent Skill poisoning. Each finding […]
Checkmarx AI Supply Chain Security (AI SCS) gives CISO, security and development teams complete visibility and control over AI components in their software supply chain. Integrated directly into the Checkmarx One platform, it uncovers hidden AI assets (LLMs, agents, MCP servers, frameworks) evaluates AI-specific risks like insecure deserialization, dangerous model loaders, shell execution, suspicious pickle/torch gadget patterns, enforces governance through your existing AppSec workflows and generates AI-BOM.
Checkmarx One AI Supply Chain Security Read Post »
An automated testing and monitoring application that uses novel, multi-turn, and use-case-specific attacks Ñ enabling stakeholders to continuously identify, document, and remediate GenAI vulnerabilities according to industry-standard mitigations throughout the application development cycle.
A privacy-focused code scanner that detects AI integrations embedded in code, including shadow AI, blocks unapproved data types in LLM prompts and other risky data sinks before any code reaches production, and generates audit-ready Privacy Impact Assessments prefilled with detected data flows and privacy risks.
HoundDog.ai Privacy-by-Design Code Scanner for AI Applications Read Post »
NeuralTrust MCP Scanner verifies MCP connectors and servers by scanning code, manifests, dependencies, and access configurations to detect vulnerabilities, poisoned tools, insecure defaults, and overly broad permissions before deployment.
NeuralTrust Generative Application Firewall enables continuous vulnerability scanning and behavioral threat detection by analyzing LLM interactions, identifying anomalies, multi-turn attack patterns, and semantic exploits in real time to enforce policies and prevent misuse before escalation.
Embed privacy by design into every stage of development by scanning code from IDE to CI/CD. Discover AI integrations, including shadow AI, detect exposures of PII, PHI, and authentication tokens in LLM prompts and other often-overlooked surfaces such as logs, files, and third-party SDKs, and block unapproved data types before any code reaches production.
Privacy-focused Code Scanner for AI Applications Read Post »
Prisma Cloud AI-SPM helps organizations discover, classify, protect and govern AI-powered applications. It provides visibility into the entire AI ecosystem including model, applications and resources, to reduce the risk of data exposure and compliance breaches. By identifying model vulnerabilities and prioritizing misconfigurations, it improves the integrity of the AI security framework.
Prisma Cloud AI-SPM Read Post »
Unified AI security platform that governs and secures all AI activity across employees, models, applications, and agents; delivers bidirectional runtime protection including against prompt injection and jailbreaks; and provides automated red teaming for LLM applications.
AIandMe provides an end-to-end platform for testing, securing, and monitoring LLM-based AI systems—combining automated adversarial testing, real-time protection, and human-in-the-loop audits to ensure reliable, compliant, and safe AI deployments.