cve-triage

cve-triage is a skill for Claude Code from UnitOneAI/SecuritySkills. It costs 86 tokens per session (5,538 once invoked), scanned C, original, MIT.

A process for deciding how urgently to fix a software vulnerability identified by a CVE, the standard identifier assigned to a known security flaw. It combines severity, real-world exploitation evidence, attack likelihood, and business context.

In plain words
What is it for?
Prioritizing CVE backlogs, reviewing vulnerability scan results, deciding whether a vulnerability should be patched, checking known exploited vulnerabilities, and assigning remediation service levels.
Why use it?
It helps security teams focus limited patching time on vulnerabilities most likely to cause harm instead of treating every scanner result the same. It also assigns practical remediation deadlines.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Prioritizing CVE backlogs, reviewing vulnerability scan results, deciding whether a vulnerability should be patched, checking known exploited vulnerabilities, and assigning remediation service levels.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/unitoneai/securityskills/cve-triage
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 UnitOneAI/SecuritySkills --skill cve-triage
Clone the repo
git clone --depth 1 https://github.com/UnitOneAI/SecuritySkills

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-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/unitoneai/securityskills/cve-triage.svg)](https://agentmods.dev/skills/unitoneai/securityskills/cve-triage)
Your own site
<a href="https://agentmods.dev/skills/unitoneai/securityskills/cve-triage"><img src="https://agentmods.dev/badge/skills/unitoneai/securityskills/cve-triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,538 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00086 $0.05538
Opus 5 $0.00043 $0.02769
Sonnet 5 $0.00017 $0.01108
Haiku 4.5 $0.00009 $0.00554

Measured 8d ago against content hash 0438bb065287, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

cve-triage scanned grade C with 2 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 8d ago.

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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- CISA KEV catalog version: !`curl -sf https://www.cisa.gov/sites/default/files/feeds/known_exploited_vulnerabilities.json | python3 -c "import sys,json; d=json.load(sys.stdin); print(f'v{d.get(\"catalogVersion\",\"unkno

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- CISA KEV catalog version: !`curl -sf https://www.cisa.gov/sites/default/files/feeds/known_exploited_vulnerabilities.json | python3 -c "import sys,json; d=json.load(sys.stdin); print(f'v{d.get(\"catalogVersion\",\"unkno
skills/vuln-management/cve-triage/SKILL.md · 444 lines

How it starts

The opening of the file, as written. The whole thing — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CVE Triage & Prioritization -- CVSS 4.0 / SSVC 2.1 / EPSS / CISA KEV

Live Context (auto-populated)

  • CISA KEV catalog version: !curl -sf https://www.cisa.gov/sites/default/files/feeds/known_exploited_vulnerabilities.json | python3 -c "import sys,json; d=json.load(sys.stdin); print(f'v{d.get(\"catalogVersion\",\"unknown\")} ({d.get(\"count\",\"?\")} entries, updated {d.get(\"dateReleased\",\"unknown\")})')" 2>/dev/null || echo "unavailable -- use WebFetch to query manually"

Frameworks: CVSS 4.0 (FIRST.org), SSVC 2.1 (CERT/CC), EPSS (FIRST.org), CISA KEV Role: SOC Analyst, Security Engineer, vCISO Time: 10-20 min per CVE Output: Prioritized remediation recommendation with SLA assignment, SSVC decision, and business risk context


When to Use

If a target is provided via arguments, focus the review on: $ARGUMENTS

Use this skill when a CVE identifier appears in conversation, when vulnerability scan results (Qualys, Tenable, Rapid7, Snyk, Trivy, Grype) are shared, when a user asks "should we patch this?", or when prioritizing a backlog of vulnerabilities for remediation. This skill converts raw vulnerability data into actionable, SLA-bound remediation decisions.

Do not use when: The task is about writing detection rules (use detection-engineering), performing forensic investigation of an exploited vulnerability (use ir-playbook), or analyzing software composition without CVE context (use sbom-analysis).


Context the Agent Needs

Before starting, collect or confirm:

  • CVE ID(s): The specific CVE identifier(s) to triage (e.g., CVE-2024-3094)
  • Affected software/version: Product name, version, and component (e.g., OpenSSL 3.0.2, xz-utils 5.6.0)
  • Deployment context: Where is this software running? (Internet-facing, internal, air-gapped)
  • Business criticality: What business function does the affected system support? (Revenue-generating, customer-facing, internal tooling, development)
  • Compensating controls: Are there existing mitigations in place? (WAF, network segmentation, EDR, disabled feature)
  • Compliance requirements: Any regulatory mandates affecting patch timelines? (CISA BOD 22-01 for federal, PCI DSS, HIPAA)

Read the full file on GitHub · 444 lines

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. 8d ago First seen · 444 lines · 86 tokens per session scan C 0438bb065287

Subscribe to this mod's changes

cve-triage is a skill published in the GitHub repository UnitOneAI/SecuritySkills (60 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 5,538 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.