Bright DAST discovery, scanning, and remediation for Claude Code: register endpoints from the code, run scans through a Repeater, and fix findings via the Bright MCP server.
Plugin bright-security from marketplace brightsec in BrightSec/bright-ai-plugins. Commands read from the repo's manifest — 22 days ago.
analyze-codebaseDetect the technology stack and inventory the HTTP endpoints that can be scanned through Bright DAST, excluding those whose effects cannot be undone.
compose-harRegister many routes of one credential through one archive discovery, not one login per entrypoint — compose a HAR 1.2 file, discover it, and reconcile each entry with its entrypoint.
fix-and-validateApply minimal fixes for Bright findings and verify them by re-running the same scan configuration over the same target surface.
register-entrypointsRegister the application's operations in Bright as entrypoints from its source code, with code-grounded parameter values, health checks, and named gaps; crawl only as a fallback.
run-scanSelect Bright security tests, run scans against registered entrypoints, monitor execution, and retrieve findings.
setup-authMap the application's authentication mechanisms from its code and create a verified Bright auth object for each one the inventory needs.
setup-repeaterEstablish the Bright project for the run and, for private or local targets, create or reuse a Repeater and connect it to the application under test.
bright-application-testingAnalyze the repository, register its entrypoints in Bright, and run DAST scans; reports findings and changes no code.
bright-discoveryBuild the endpoint list of the application under test whitebox from its source code, register the endpoints in Bright with code-grounded parameter values, check them against Bright, and report what could not be registered and why — discovery only, no scanning and no code changes.
bright-remediation-loopRun Bright DAST, apply minimal code fixes for confirmed findings, and re-run the same validation scans until the vulnerability disappears or the round limit is reached.
brightsecconnects to: https://${BRIGHT_HOSTNAME}/mcp
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.
hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
SAST analysis, dependency vulnerability scanning, OWASP Top 10 compliance, container security scanning, and automated security hardening
5 skills · 3 commands · 2 agents
Connect Claude to Prowler Cloud through the Prowler MCP server. Reads providers, scans, findings, compliance results and resources for AWS, Azure, GCP, Kubernetes, Microsoft 365, GitHub and the other providers listed at https://registry.prowler.com, and returns remediation guidance for failed checks. Writes are limited to Prowler Cloud itself: triggering scans, finding triage, mute rules and the mutelist, providers and integrations. Your cloud resources are not changed by the connector.
1 skill · 1 MCP server
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.
2 skills · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.