Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Site Security

ASecurity

Use when the user asks to "scan my site for vulnerabilities", "what CVEs does X have", "security coverage for", "check my site's security", or runs /aegis:scan. Produces a prioritized passive vulnerability-coverage report from a site's fingerprint — known CVEs (OSV-first) ranked by CISA KEV + EPSS, plus TLS/header misconfig. Passive lookup only (no active probing).

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentspythonbashsecurity

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add neotherapper/claude-plugins --skill site-security --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Site Security?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Site Security
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/neotherapper-site-security/badge)](https://www.skillsdirectory.com/skills/neotherapper-site-security)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: site-security
description: Use when the user asks to "scan my site for vulnerabilities", "what CVEs does X have", "security coverage for", "check my site's security", or runs /aegis:scan. Produces a prioritized passive vulnerability-coverage report from a site's fingerprint — known CVEs (OSV-first) ranked by CISA KEV + EPSS, plus TLS/header misconfig. Passive lookup only (no active probing).
license: MIT
metadata:
  version: "0.1.0"
  author: Georgios Pilitsoglou
---

# site-security — Passive Vulnerability Coverage

Produce a prioritized security-coverage report for a target site. This is a **passive
lookup only** — it queries public CVE feeds and grading services, never probes the target.

**v0.1 scope:** passive data-lookup (OSV, NVD, KEV, EPSS, SSL Labs, Mozilla Observatory).
Active scanning / exploit confirmation is a future v0.2 step requiring explicit authorization.

## Quickstart

Resolve the target (slug or URL), then run the orchestrator:

```bash
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/coverage.py" --slug {slug}
# or
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/coverage.py" --url {url}
```

Output is written to `docs/sites/{slug}/security/coverage.{json,md}`.

## Workflow

1. **Resolve target.** Accept a URL or a site slug. If a URL is given, derive the slug
   (host dots → dashes). If a beacon research folder exists (`docs/sites/{slug}/research/`),
   the fingerprint stage reuses it automatically.

2. **Run coverage.py.** The orchestrator chains: fingerprint → OSV/NVD CVE lookup →
   KEV/EPSS overlay → SSL Labs / Observatory misconfig → report.

3. **Present results.** Show the report summary, **KEV/high-EPSS items first**:
   - Components found and CVE count
   - KEV exploited CVEs (highest priority)
   - High CVSS + high EPSS CVEs
   - Misconfig grades (TLS, headers)
   - Any coverage-incomplete sources (never silently ignored)

4. **Honesty notes.** Always surface:
   - `[VERSION-UNKNOWN]` components (version missing → not assessed, not clean)
   - `coverage_incomplete` sources (feed failures → gaps, not zero-vulns)
   - This is passive lookup — active confirmation is a separate future step

## Data Sources

| Source | Purpose | Auth |
|--------|---------|------|
| OSV.dev | Package CVE lookup (npm, PyPI, etc.) | none |
| NVD | Framework/server keyword CVE search | none |
| CISA KEV | Exploited-in-the-wild overlay | none |
| FIRST EPSS | Exploit likelihood overlay | none |
| SSL Labs | TLS configuration grade | none |
| Mozilla Observatory | HTTP security headers grade | none |

## Report Location

`docs/sites/{slug}/security/coverage.json` and `coverage.md`

## v0.1 Limitations (state these to the user)

- Passive only — no active scanning or exploit confirmation
- CVE coverage depends on OSV/NVD feed completeness
- Missing component versions → reported as `[VERSION-UNKNOWN]`, not "clean"
- SSL Labs and Observatory are asynchronous — may timeout on complex sites

Attribution

neotherapperneotherapper
View sourceSee grades on GitHubMore from neotherapper →
SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1087401 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

697551 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →