Search Results for "vulnerability"

The open-source Agentic LLM Vulnerability Scanner.

Trail of Bits Skills Marketplace is a specialized Claude Code skills marketplace built by the security research firm Trail of Bits that focuses on enhancing AI-assisted workflows for vulnerability discovery, testing, and secure development. The repository groups a set of plug-in skills tailored toward static analysis, code auditing, secure defaults detection, and other practices that matter in software security. Users can easily add the marketplace to a Claude Code environment, browse available plugins, and install specific skills for tasks like automatic Semgrep rule creation, entry-point analysis in smart contracts, or insecure defaults detection. ...

AutoCVE is an agent-driven platform for automating authorized source-code auditing and CVE discovery. It covers the workflow from project selection and repository import to vulnerability verification and submission-ready report generation. An orchestrator coordinates specialized agents for reconnaissance, scanning, triage, deep analysis, verification, and final consolidation. Users can choose enhanced scanning, intelligent auditing, or comprehensive auditing based on speed and depth requirements. The interface records agent trees, tool calls, phase progress, sessions, findings, and supporting evidence for review. ...

AI-Infra-Guard is a powerful open-source security platform from Tencent’s Zhuque Lab designed to assess the safety and resilience of AI infrastructures, codebases, and components through automated scanning and evaluation tools. It brings together AI infrastructure vulnerability scanning, MCP server risk analysis, and jailbreak evaluation into a unified workflow so that enterprises and individuals can identify critical security issues without relying on external services. Users can deploy it via Docker or scripts to get a modern web UI that guides them through tasks like scanning third-party frameworks for known CVEs and experimenting with prompt security against attack vectors. ...

...It combines LLM agents, MCP toolchains, penetration testing skills, and command-line automation to support authorized security assessments. The project can guide information gathering, vulnerability discovery, validation, and report generation while keeping the workflow organized through sessions and tools. Its newer architecture uses a goal-driven solving engine instead of a fixed-round loop, helping the agent stop when the goal is reached, the search space is exhausted, or a safety budget is met. It also includes evidence checks designed to reduce hallucinated conclusions by requiring real tool output before accepting key findings. ...

PentestAgent is an open-source autonomous security testing platform designed to help organizations identify vulnerabilities and assess security posture by simulating real-world attack scenarios without manual intervention. It brings a modular and automated approach to penetration testing by orchestrating a suite of tools and scripts that can emulate common exploitation techniques, reconnaissance workflows, and post-exploitation activities across targets. Users configure rules, policies, and...

AI-Infra-Guard is an open-source AI red teaming platform for evaluating security risks across modern AI ecosystems. It combines scanning for AI agents, agent skills, MCP servers, AI infrastructure, and OpenClaw deployments. Its infrastructure scanner fingerprints AI services and checks them against a large library of known vulnerabilities. Agent and skill analysis detects risks involving malicious instructions, unsafe code execution, privilege abuse, compromised tools, and insecure...

...The core message. HunterX does not stop at finding a possible vulnerability. It is built to investigate the hypothesis, validate the behavior, prove the finding, reproduce the evidence, assess the impact, and turn the result into a report-ready security finding. Vulnerability + Evidence + Reproducibility + Proof / PoC + Impact ================ Validated Finding