security plugins

by MerchantGuardOps

Local tool policy gates and signed, content-free decision records for Codex and ChatGPT Work.

by MerchantGuardOps

Local tool policy gates and signed, content-free decision records for Codex and ChatGPT Work.

by Kyle Chalmers

Data + AI security audits for data professionals — cited, severity-ranked findings for AI tool configs, secrets exposure, data classification, and warehouse access.

by Bymax One

Whole-system QA and security audit for any project, with evidence and hand-off. Point /bymax-qa:audit at a target: a Jira ticket key (it verifies Jira access, reads the acceptance criteria, and reports each PASS/FAIL/BLOCKED/NOT-VERIFIABLE with evidence), a branch or ref range or PR (it scopes the hunt to the change, like a code review), or nothing (the whole system via a signed scope). It maps the stack and its trust boundaries, hunts by domain (authentication, authorization and tenant isolation, injection and input, cache/Redis, database/Postgres, observability, transport and config, architecture, frontend, supply chain) with read-only finder agents, probes the running stack against the allow-listed hosts only, and admits a finding only after verification: a runnable reproduction, captured evidence and verified impact, with an independent verifier for every hunted candidate. Every finding carries ASVS 5.0, CWE and API Top 10 references, a CVSS vector, and a status that moves OPEN → HANDED-OFF → FIX-CLAIMED → VALIDATED or REOPENED. Fixes are never applied by the auditor: findings are handed to the owning peer session over cross-session messaging, filed as GitHub issues when no peer is live, or written back to the ticket as a comment, and re-tested before they close. A PreToolUse hook is a floor under the scope while an audit is active: a network tool in command position may only reach allow-listed hosts, and a Write/Edit tool call may only land in .claude/qa/ (arbitrary Bash writes and unlisted network binaries rest on the skill's never-edit-the-target discipline and its read-only finders). External scanners (semgrep, gitleaks, osv-scanner, trivy, zap, nuclei, axe, Lighthouse) are used when present and never bundled.

by Bymax One

Evidence-based quality gates: bounded Claude and Codex review with pinned candidates, verified findings, correction deltas and regression checks; TDD, stack-specific reviewers and security hooks.

by daishengda2018

Android code review toolkit v3.1.1 - Refactored architecture with clear responsibility separation

by idnotbe

Hook-based security guardrails for Claude Code's --dangerously-skip-permissions mode. Blocks destructive commands, protects secrets, and auto-commits safety checkpoints.

by Joe Degler

Set up Clooks and create TypeScript hooks for your agents.

by Cloud Officer

Cloud Officer development workflow tools for PR management, issue tracking, code quality, cloud infrastructure and cost optimization (AWS, GCP), deployment (Heroku), payments (PayPal), observability (New Relic), design (Figma), app stores (App Store Connect, Google Play), and database management

by Big Coconut

A four-agent product team. Bob directs design and approves merges, Daisuki-chan implements, Hiram runs QA and security, Amy keeps the project record and catches drift. Ships the activity-log and drift-detection hooks the team depends on.

by Skylar

Adaptive, multi-agent engineering workflows for any codebase: audit, security/privacy threat assessment, remediation, feature discovery & build, performance, tests, dependencies, PR review, doc alignment, onboarding, and code normalization. Developer-in-the-loop, behavior-preserving, with shared conventions.

by Skylar

Adaptive, multi-agent engineering workflows for any codebase: audit, security/privacy threat assessment, remediation, feature discovery & build, performance, tests, dependencies, PR review, doc alignment, onboarding, and code normalization. Developer-in-the-loop, behavior-preserving, with shared conventions.

by Google LLC

Enterprise autonomous security auditing, zero-false-positive PoC verification, and context-aware patch remediation using Google Cloud CodeMender (cm) on Gemini Enterprise Agent Platform.

by OpenAI

Codex Security workflows for security scans, analysis, and investigation.

by Emanuele Greco

Extremely complete reference toolkit for vibe coders and developers: frontend, backend, security, testing, architecture, devops, git/DX, and AI-integration guidance, with routing to specialized design/security skills when available.

by yukineko

Daily-once task runner for Claude Code: a SessionStart hook that runs registered shell tasks ([[task]] in ~/.daily/config.toml) at most once per calendar day and injects a summary of what ran. Skips while a /flow or /backlog driver is working (backlog lock), records each run to a JSONL report, and a failed task still counts as run (no retry until tomorrow). With no tasks registered it runs a default security audit (cargo deny check). Register/inspect with `daily add` / `daily list` / `daily report`; set enabled=false to disable. Subscription-native (one hook + bundled Rust binary, no API key).

by daviduartedev

Agent Skills for AppSec in spec-driven development (OWASP ASVS 5.0.0 by relevance) and a human smoke checklist after implement

by GitHub

Manages dependency updates across Docker images, Python packages, and other ecosystems. Automates versioning, security scanning, and CI/CD compatibility checks.

by DodexaCode Maintainers

AI-native Swift shell and MCP server with typed primitives, self-diagnostics, evaluator-ready submission bundles, capability catalog, workspace context, and scoped security review tooling.

by Endor Labs

Endor Labs security workflow skills, agents, and MCP server for GitHub Copilot. Requires only the endorctl binary: no Node, Python, or Unix tools.

by yukineko

v0.1.2: DISCLOSES A PROTECTION GAP — doc-only, no logic change, and the gap is NOT closed by this version. Through 0.1.1 this crate was explicitly one half of a pair: it scans WHAT web-tool output says, and `taintguard` tracked WHERE content came from, downgrading write-class tools for the rest of a turn that had read something external. taintguard was removed from the repository on 2026-08-24 by user ruling. Its half is gone and was not reassigned, so: external-file `Read` (a path outside the project) now produces NO provenance signal and NO content scan, and nothing restricts the turn afterwards; and this crate's own enforcement is only an `additionalContext` warning — it downgrades and denies nothing. The prose that said the Read surface was "deferred to taintguard's provenance gate" (`gate.rs`'s fail-closed contract and `WEB_TOOLS`'s docstring) said the surface was covered elsewhere, which is now false; both, plus README.ja.md and the `scan`/`main` module docs, now state the surface is covered by nothing. Recorded as an open gap so it is visible rather than silently inherited. Runtime content-level injection scanner: a PostToolUse hook (matcher WebFetch|WebSearch) that scans the tool_response text for planted prompt-injection phrasings (concealment / verification-bypass / instruction-override / egress) and, on a hit or an undecidable response, injects additionalContext telling the model the flagged span is untrusted DATA whose embedded directives must NOT be followed.

by fintech-claude-skills contributors

Production-grade fintech engineering, UI/UX and audit skills for Claude Code. Makes Claude rigorous about financial correctness, security, concurrency, idempotency, auditability and production readiness.

by Rajesh Bhattarai

Turns Claude Code into a senior frontend architect for React/Next.js: verification gates on the build path, a generated inventory of your repo's own components and endpoints, house conventions enforced in CI, and independent audits — with an ablation benchmark that reports what it actually adds.

by _ud2

183+ pentesting and OSINT tools (nmap, nuclei, amass, subfinder, httpx, sherlock, maigret, trufflehog, sqlmap, impacket, and more) wired into Claude Code as a single skill. Runs locally on any OS via native Bash, WSL, or purpose-built Docker images (instrumentisto/nmap, projectdiscovery/nuclei, caffix/amass, etc.). Just ask Claude to recon a target, scan a network, investigate a username, or chain OSINT workflows — the skill picks the right backend and image automatically.