
seclab-taskflows
Example AI-agent taskflows and MCP servers for auditing source code, triaging issues, and detecting vulnerabilities across web, Android, and iOS…

Example AI-agent taskflows and MCP servers for auditing source code, triaging issues, and detecting vulnerabilities across web, Android, and iOS…

Open-source detection engineering tool that traces security detections end to end and identifies the first failing stage.

Opensource IDE For Exploring and Testing API's (lightweight alternative to Postman/Insomnia)

Full-stack AI security OS for your browser, terminal, and agents. Find, verify, and fix vulnerabilities. Prioritized by business impact instead of…

Multi-agent static application-security review harness for AI coding agents: maps codebases, hunts vulnerability classes, chains and verifies…

Evidence and data for the Sorami technical report on security defaults of 15 AI serving, vector database and MCP Helm charts on Kubernetes.

A deterministic network sandbox for testing nftables rules. It uses ephemeral Linux network namespaces (netns) and Scapy to validate firewall logic…

Safety cannot be a prompt instruction. TBP provides an external execution-layer boundary for autonomous agents, enforcing hard F/I/W invariants via…

Sandboxed runtime for autonomous AI agents with declarative YAML policies enforcing filesystem, network, and process constraints, plus endpoint-bound…

Sandbox and MCP proxy that blocks AI coding agents from reading SSH keys, AWS credentials, and .env files, with deny-by-default policy and…

eBPF-based Linux agent that enforces executable-level access policies in kernel space, sandboxing processes and restricting file, network, and GPU…

Deliberately vulnerable Java/Maven fixture for testing Log4Shell (CVE-2021-44228) detection, code-impact classification, and remediation guidance in…

Policy-governed LLMSecOps framework providing AST-based SAST, secret scanning, supply-chain and multi-cloud CSPM checks, AI-BoM generation, and CI/CD…

Cross-check the views of your attack surface and find the endpoints that cannot corroborate each other.

Read-only CLI that inventories AI agents, MCP servers, plugins, and extensions on a machine, reporting their capabilities and exposure with…

Open source CSPM for Azure - scan for misconfigurations and quantum-unsafe cryptography, map findings to CIS/NIST/ISO27001/SOC2, and fix them with…

GitHub Action for Offensive360 SAST scans and SARIF results. See the open-source program for eligibility and setup.

MCP server that runs SAST scans on local codebases and returns findings with severity and fixes, enabling AI assistants to perform security analysis…