cve-severity-analysis

cve-severity-analysis is a skill for Claude Code from mappedsky/seizu. It costs 45 tokens per session (620 once invoked), scanned A, original, Apache-2.0.

A statistics tool for analysing CVEs, which are public records of software security flaws, using their CVSS severity scores. It compares recent CVEs with all-time severity counts over a chosen time window.

In plain words
What is it for?
Use it to measure how many recent CVEs are critical, high, medium, or low severity and examine their score statistics.
Why use it?
It turns a list of security flaws into counts, score distributions, percentiles, and severity comparisons that are difficult to obtain from a graph query alone.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to measure how many recent CVEs are critical, high, medium, or low severity and examine their score statistics.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mappedsky/seizu/cve-severity-analysis
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add mappedsky/seizu --skill cve-severity-analysis
Clone the repo
git clone --depth 1 https://github.com/mappedsky/seizu

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cve-severity-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/mappedsky/seizu/cve-severity-analysis/github.svg)](https://agentmods.dev/skills/mappedsky/seizu/cve-severity-analysis)
Your own site
<a href="https://agentmods.dev/skills/mappedsky/seizu/cve-severity-analysis"><img src="https://agentmods.dev/badge/skills/mappedsky/seizu/cve-severity-analysis/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cve-severity-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/mappedsky/seizu/cve-severity-analysis"><img src="https://agentmods.dev/badge/skills/mappedsky/seizu/cve-severity-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 620 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.00620
Opus 5 $0.00023 $0.00310
Sonnet 5 $0.00009 $0.00124
Haiku 4.5 $0.00005 $0.00062

Measured yesterday against content hash 38216b55764a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

cve-severity-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.config/dev/seizu/plugins/cve-response/skills/cve-severity-analysis/SKILL.md · 36 lines

What it actually says

Compute a CVSS score distribution and severity breakdown for CVEs in the NVD-synced graph over the window the hours input names.

This analysis requires numeric computation that goes beyond what a graph query returns directly — use sandbox__delegate for the entire workflow. The sandbox agent has direct access to the cve_analysis tools (they are available in its tool list) and can call them to fetch data, then run Python for the statistics.

Inputs:

  • hours — the window to analyse, in hours. Defaults to 168.

Task to pass to sandbox__delegate:

You have access to graph tools including cve_analysis__get_recent_cves and cve_analysis__count_cves_by_severity. Use them to fetch data, then run Python to compute statistics.

  1. Call cve_analysis__get_recent_cves with hours= the hours input and severity="" (empty string, no filter) to retrieve all CVEs published in the window. Each row returns: id, severity, base_score, epss_score, published.
  2. Call cve_analysis__count_cves_by_severity (no parameters) for an all-time severity count for context.
  3. Using Python, compute from the get_recent_cves results: a. Count of CVEs in the window per severity tier (CRITICAL / HIGH / MEDIUM / LOW / NONE / unknown) b. Percentage of each tier out of total window CVEs c. Average base_score across all CVEs in the window that have a non-null score d. Average base_score per severity tier (omit tiers with no scored CVEs) e. CVSS score percentiles across all scored CVEs in the window: P25, P50, P75, P90, P95 f. Top 10 CVEs by base_score (id, severity, score, published date)
  4. Return a markdown report structured as:
    • CVE Risk Distribution — Last Hours, with the window substituted

    • One-line summary: total CVEs in window, breakdown by severity, and all-time total from step 2
    • Severity Distribution table: Severity | Count | % of Window | Avg Score
    • CVSS Percentiles table: P25 | P50 | P75 | P90 | P95
    • Top 10 CVEs by Score table: CVE ID | Severity | Base Score | Published

Present the markdown report from the sandbox agent directly as your response.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 36 lines · 45 tokens per session scan A 38216b55764a

Subscribe to this mod's changes

cve-severity-analysis is a skill published in the GitHub repository mappedsky/seizu (5 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 620 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-11.

Related

Other skills, from other repositories

tutti-agent-workspace-app

Build or evolve a complex agent-enabled Tutti workspace app repository. Use for Tutti apps with web/server/shared monorepos, @tutti-os/agent-acp-kit local agent runtimes, kit-owned TUTTICLI agent/composer discovery, dynamic agent catalogs, run-scoped MCP tool gateways, app-owned package builders, web-first debugging…

tutti-os/tutti · 106 tokens

assimilate-popular-workflows

This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable…

a5c-ai/babysitter · 110 tokens

mcp-app-verification

Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.

a5c-ai/babysitter · 48 tokens

verification-suite

Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.

a5c-ai/babysitter · 36 tokens

mcp-app-scaffolding

Scaffolds MCP App project structure with correct directory layout, dependencies, entry points, and framework-specific templates. Handles React (useApp hook), Vanilla JS, Vue, Svelte, Preact, and Solid.

a5c-ai/babysitter · 50 tokens

mcp-csp-investigation

Comprehensive Content Security Policy audit for MCP Apps in sandboxed iframes. Discovers all network origins, traces them to source, and generates CSP configuration for registerAppResource.

a5c-ai/babysitter · 43 tokens