26,946 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Skill Claude CodeCodex
Use before committing to the public CTObot repo to catch company-specific or proprietary content that has drifted into the public files (AGENTS.md, SOUL.md, docs/, skills/, README). The agent reads the diff (or all files) and reasons about whether the content is generic and shareable or specific to our company…
Skill Claude CodeCodex
Scans Claude Code skills for security risks before installation. Checks for prompt injection, credential harvesting, exfiltration patterns, hooks, excessive permissions, and settings modification. Supports GitHub URLs, local paths, and bulk scanning. Use when asked to audit, scan, or check a skill for malware or…
chenxihuang1028-a11y/variant-analysis
Skill Codex
Find similar vulnerabilities and bugs across codebases using pattern-based analysis. Use when hunting bug variants, building CodeQL/Semgrep queries, analyzing security vulnerabilities, or performing systematic code audits after finding an initial issue.
yanis7774/mac-security-audit-skill
Skill Claude CodeCodex
Run a comprehensive READ-ONLY macOS security audit and triage the findings. Checks open/listening ports and external exposure, firewall + stealth, SSH and remote access (Screen Sharing, ARD), VPN/tunnels (Tailscale, WireGuard, reverse SSH), persistence (LaunchAgents/Daemons, cron, login hooks, shell rc, BTM /…
Skill Claude CodeCodex
VirusTotal antivirus and active protection for OpenClaw: file/hash lookup, background scanning with policy-controlled uploads, command inspection and blocking, and quarantine of malicious auto-scan results. Use for file threat analysis or an explicit request to manage these protections. Includes persistent…
Open-Paws/cryptpad-project-management
Command Claude Code
Node.js modules handling authenticated RPC commands from clients. The server never decrypts document content — it only processes metadata, access control, and storage operations on encrypted blobs and public keys.
Plugin Claude Code
Bundles 11 skills, 1 hook · 825 tokens together
Socratic lenses for software engineering: question batteries that examine your work from security, design, usability, test-quality, and operational-recovery perspectives — plus an orchestrator that surfaces caveats, rabbit holes, and blast radius before you build, and a memory loop that grows new lenses from your real.
dungnotnull/dex-market-manipulation-detector-agent-skill
Skill Claude CodeCodex
This document serves as the authoritative registry for all skills in the dex-market-manipulation-detector harness. It documents how skills are registered, resolved, executed, and validated, including input/output JSON schemas for runtime validation and automatic documentation generation.
Command Claude Code
You are a security expert specializing in dependency vulnerability analysis, SBOM generation, and supply chain security. Scan project dependencies across multiple ecosystems to identify vulnerabilities, assess risks, and provide automated remediation strategies.
get-convex/convex-codex-plugin
Skill Claude CodeCodex
Audit and harden a Convex app's authorization: identity-from-arg impersonation, missing per-document ownership checks, and public queries leaking PII/financial data by a client-supplied id — the single largest real-defect cluster measured against generated Convex backends (44 of 214). Runs a deterministic scan for the…
mumuchongchongchong/security-skills
Skill Codex
Offline reconstruction and security audit of agent execution traces from JSON, JSONL, or pasted logs. Use when Codex needs to review user input, model planning, tool calls, tool results, approvals, and final answers for prompt injection, unauthorized tools, secret exposure, missing approval, repeated-call loops, or…
jiluojiluo/agent-skill-sandbox-configurator
Skill Claude CodeCodex
A setup tool for running an agent skill inside an OpenSandbox isolation environment. It examines the skill and creates the files needed to build and use a Docker-based sandbox.
Skill Claude CodeCodex
Analyze JSON Web Tokens (JWTs) for common security vulnerabilities including algorithm confusion attacks (RS256 to HS256), none algorithm bypass, weak secret brute-forcing, and claim manipulation. Practice in isolated lab environments to understand authentication bypass and privilege escalation via token forgery.
newcore-network/opencore-ai-skills
Skill Claude CodeCodex
OpenCore framework best practices - bootstrap, controllers, imports, security, events, type generation, adapters, validation, runtime constraints. Use this skill when writing, reviewing, refactoring, or explaining code built with @open-core/framework and related OpenCore adapters. Trigger on any question about…
Plugin Claude Code
Bundles 1 skill, 27 commands · 451 tokens together
GRC (Governance, Risk, and Compliance) domain knowledge — frameworks, controls, audits, evidence, ConMon, cross-framework mappings, document review, and operational workflows. Cloud-agnostic.
Plugin Claude Code
Bundles 1 skill, 1 command, 1 agent · 166 tokens together
AI-powered security review of code changes via /stride-security-review:security-review — diff or full-repo scans with framework rule packs for web, mobile and CI/CD. Emits SARIF with severity gating for CI, plus a considerations mode that checks a task's securityconsiderations were mitigated.
ManuelBerrueta/hacking-buddy-mcp
MCP server Claude CodeCodexCursor +2
MCP server "hacking-buddy-mcp" as configured in ManuelBerrueta/hacking-buddy-mcp. Runs locally from the hacking-buddy-mcp Python package.
MCP server Claude CodeCodexCursor +2
Scan a repo for hidden prompt-injection payloads before your AI agent trusts it. Runs locally from the malskanner npm package.
Skill Claude CodeCodex
Intelligent code security scanner with hybrid local-cloud detection. Fingerprints packages, runs static behavioral analysis, and consults cloud threat intelligence (enabled by default, can be disabled) for confidence scoring.
MCP server Claude CodeCodexCursor +2
MCP server "bugbounty-mcp-server" as configured in akinabudu/bug-bounty-mcp. Runs locally from the bugbounty-mcp-server Python package.
MCP server Claude CodeCodexCursor +2
MCP-first smart contract attack engine for AI developer tools. Runs locally from the raze-security npm package.
knethteo/tenable-identity-exposure-mcp
MCP server Claude CodeCodexCursor +2
MCP server "tenable-tie-mcp" as configured in knethteo/tenable-identity-exposure-mcp. Runs locally from the tenable-tie-mcp Python package.
broven/claude-permissions-plugin
Plugin Claude Code
Bundles 1 skill, 1 hook · 2 tokens together
Bash permission management for Claude Code: auto-approve compound commands, sync project permissions to global settings, and analyze permission logs to discover missing allow rules.
Nelsonochoam/nelsonochoam-claude-plugins
Plugin Claude Code
Bundles 1 skill · 0 tokens together
QA artifact generator — point it at a PR or give freeform instructions. Navigates the UI, captures screenshots, and stitches a GIF. Fully configurable auth and artifact storage via /.sentinel/config.json.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: