analyze-cve-repos

analyze-cve-repos is a skill for Claude Code from openshift-eng/ai-helpers. It costs 21 tokens per session (1,830 once invoked), scanned A, original, Apache-2.0.

A security-analysis skill that checks whether code affected by a CVE can actually be reached in downstream repository forks at the relevant release branch. A CVE is a publicly recorded software vulnerability, and a release branch is the code line used for a shipped version.

In plain words
What is it for?
Use it during CVE triage to analyze vulnerable paths in downstream repositories and mark cases uncertain when the required fork or branch is missing.
Why use it?
It avoids treating every reported vulnerability as exploitable when the affected code path may not be present or reachable in the shipped repository.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the node-cve plugin — 3 skills shipped together

Good fit Use it during CVE triage to analyze vulnerable paths in downstream repositories and mark cases uncertain when the required fork or branch is missing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openshift-eng/ai-helpers/analyze-cve-repos
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 openshift-eng/ai-helpers --skill analyze-cve-repos
Clone the repo
git clone --depth 1 https://github.com/openshift-eng/ai-helpers

Made for: Claude Code.

Or install node-cve, the plugin that ships this one along with the rest of its 3 skills.

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 analyze-cve-repos

README.md
[![agentmods](https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/analyze-cve-repos/github.svg)](https://agentmods.dev/skills/openshift-eng/ai-helpers/analyze-cve-repos)
Your own site
<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/analyze-cve-repos"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/analyze-cve-repos/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 analyze-cve-repos

Your own site · 80×15
<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/analyze-cve-repos"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/analyze-cve-repos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,830 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00021 $0.01830
Opus 5 $0.00010 $0.00915
Sonnet 5 $0.00004 $0.00366
Haiku 4.5 $0.00002 $0.00183

Measured 7d ago against content hash fda493b90a54, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

analyze-cve-repos 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 7d 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.

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.

plugins/node-cve/skills/analyze-cve-repos/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to Use

Use this skill when Phase 2 of the node-cve:triage command needs to determine whether a CVE's vulnerable code path is actually reachable in a Node team repository. Each CVE is analyzed against the release branch corresponding to the auto-detected latest OCP version (one agent per CVE). Analysis targets downstream forks only; if the downstream fork or branch is not found, the CVE is classified as Uncertain.

Prerequisites

  • Repository already cloned to .work/node-cve/repos/<repo-name>-<branch>/ (the triage command clones all repos at the correct branch before spawning parallel analysis agents)
  • Network access to GitHub (for CVE data)

Implementation Steps

Step 1: Map component to downstream repository and branch

Analysis must target the release branch corresponding to the affected OpenShift version. The main branch may have newer dependencies or Go versions that mask vulnerabilities present in shipped releases. Analysis must target downstream forks only. If the downstream fork or branch does not exist, classify as Uncertain with note "downstream fork/branch not found" and skip analysis.

Component to repository mapping: Read the component-to-repo table and pscomponent: label mappings from the node-team shared components reference.

Version mapping: Read from the node-team shared version map. For OCP 4.Y, the formula is K8s/CRI-O minor = Y + 13. Use the formula and branch naming conventions to derive the correct release branch for each repo.

If the component does not map to a known repo, classify as Uncertain and skip analysis. If the downstream fork or release branch does not exist, classify as Uncertain with note "downstream fork/branch not found" and skip analysis.

Step 2: Verify repository and branch

The repository should already be cloned at the correct branch to .work/node-cve/repos/<repo-name>-<branch>/ by the triage command before this skill runs. Verify the directory exists and the checked-out branch matches the expected release branch. If the repo directory does not exist, classify as Uncertain and skip analysis.

Read the full file on GitHub · 150 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. 7d ago First seen · 150 lines · 21 tokens per session scan A fda493b90a54

Subscribe to this mod's changes

analyze-cve-repos is a skill published in the GitHub repository openshift-eng/ai-helpers (116 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 1,830 once invoked, about $0.0001 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 2026-09-05.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens