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.
npx skills add mappedsky/seizu --skill cve-severity-analysisgit clone --depth 1 https://github.com/mappedsky/seizuWrote 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.
[](https://agentmods.dev/skills/mappedsky/seizu/cve-severity-analysis)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
- Call cve_analysis__get_recent_cves with
hours=thehoursinput and severity="" (empty string, no filter) to retrieve all CVEs published in the window. Each row returns: id, severity, base_score, epss_score, published. - Call cve_analysis__count_cves_by_severity (no parameters) for an all-time severity count for context.
- 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)
- 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.
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.
- yesterday First seen · 36 lines · 45 tokens per session scan A 38216b55764a
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.
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…
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…
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.
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.
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.
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.