scope-enforcement

Here are 6 public repositories matching this topic...

mukul975 / Threatswarm

27 scope-enforced AI agents that run the full pentest kill-chain (recon → exploit → post-ex → DFIR → report) as a one-command Claude Code plugin. Backed by 754 MITRE-mapped skills.

Updated Apr 29, 2026
Python

Dreamcoder08 / pactyra

Star

Specification and architecture preview for authorized, evidence-backed offensive operations.

offensive-security security-tools cyber-range scope-enforcement evidence-chain authorized-security

Updated Sep 27, 2026
Go

josharsh / stay-focused

Star

A Claude Code skill that keeps edits surgical. Detects out-of-scope modifications and flags unasked changes before they happen.

developer-tools code-review ai-coding claude-code claude-code-skill scope-enforcement surgical-edits

Updated May 9, 2026
Shell

mdfifty50-boop / scope-guard-mcp

Star

MCP server that enforces multi-agent scope boundaries — prevents scope drift, work duplication, and infinite delegation loops in agentic systems

mcp permissions multi-agent ai-agents llm-tools model-context-protocol mcp-server scope-enforcement

Updated Apr 24, 2026
JavaScript

tuktukerz / boundhound

Star

🐕 Autonomous pentest framework for Claude Code with enforced, deny-by-default scope safety — recon → bounded exploit → report, one command, fully audited.