A vulnerability-checking skill for project dependencies, package versions, and CVE identifiers. It uses OSV.dev and NVD, two public sources of known software vulnerabilities.

Use it to scan package.json, requirements.txt, or dependency lists, check one package version, or look up a CVE. It can produce vulnerability findings and fixed versions where available.

It helps identify known security problems in dependencies instead of relying on memory or checking packages manually. It also highlights limits such as skipped unpinned requirements and versions that may differ from the lockfile.

vuln-scan — Skill for Claude Code by Agam-S/Vulnary-MCP

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 Agam-S/Vulnary-MCP --skill vuln-scan

Clone the repo

git clone --depth 1 https://github.com/Agam-S/Vulnary-MCP

Made for: Claude Code.

Or install vulnary, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/agam-s/vulnary-mcp/vuln-scan/github.svg)](https://agentmods.dev/skills/agam-s/vulnary-mcp/vuln-scan)

Your own site

<a href="https://agentmods.dev/skills/agam-s/vulnary-mcp/vuln-scan"><img src="https://agentmods.dev/badge/skills/agam-s/vulnary-mcp/vuln-scan/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/agam-s/vulnary-mcp/vuln-scan"><img src="https://agentmods.dev/badge/skills/agam-s/vulnary-mcp/vuln-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 480 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.

Model	Per session	Once invoked
Fable 5.1	$0.00082	$0.00480
Opus 5.5	$0.00033	$0.00192
Sonnet 5.5	$0.00016	$0.00096
Haiku 4.5	$0.00008	$0.00048

Measured 21d ago against content hash 565dd3554f4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vuln-scan 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 21d 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.

skills/vuln-scan/SKILL.md · 33 lines

What it actually says

Vulnerability scan

Use the Vulnary MCP tools. Do not guess vulnerability data from memory; always call a tool.

Pick the tool

User has	Tool
A CVE ID (e.g. `CVE-2021-44228`)	`lookup_cve`
One package + version	`check_package` (needs `ecosystem`: npm, PyPI, crates.io, Go, Maven, RubyGems, NuGet)
A list of packages in one ecosystem	`scan_dependencies`
A `package.json` or `requirements.txt` in the project	Read the file, then pass its raw contents to `scan_dependency_file`

For other manifests (Cargo.toml, go.mod, pom.xml, Gemfile, .csproj), read the file yourself, extract { name, version } pairs and call scan_dependencies with the matching ecosystem.

Limits to tell the user about

scan_dependency_file strips a leading ^ or ~ and checks that version only. It does not read lockfiles, so the installed version may differ. If a lockfile exists, prefer extracting exact versions from it and calling scan_dependencies.
requirements.txt lines without a pinned == version are skipped. Mention any you skipped.
NVD rate-limits unauthenticated requests; if lookup_cve fails, wait and retry once.

Report

One line: how many packages scanned, how many vulnerable.
A table of vulnerable packages only: package, current version, vulnerability IDs, severity, fixed in.
The upgrade to make for each one (lowest fixed_in version above the current one). If fixed_in is empty, say no fix is published yet.
Offer to apply the upgrades. Do not edit dependency files unless the user agrees.

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.

21d ago First seen · 33 lines · 82 tokens per session scan A 565dd3554f4d

Subscribe to this mod's changes

vuln-scan is a skill published in the GitHub repository Agam-S/Vulnary-MCP (1 stars, last pushed 21d ago), licensed MIT. It adds 82 tokens to every session and 480 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-18.