vulnpilot-mcp: Skill for Claude Code

.agents/skills/oss-audit/SKILL.md

oss-vulnerability-audit is a skill for Claude Code, Codex from arojit/vulnpilot-mcp. It costs 45 tokens per session (690 once invoked), scanned A, original, Apache-2.0.

A skill for checking open-source software dependencies for publicly known security weaknesses, including CVEs, which are identifiers for reported vulnerabilities. It uses the VulnPilot MCP server and supports Python, npm, Maven, and Gradle projects.

In plain words
What is it for?
Reading dependency manifests and lock files, checking package versions, analyzing reachability, and producing a security or supply-chain risk report.
Why use it?
It helps identify vulnerable packages and assess whether a vulnerability can be reached from the project. It also keeps unverified findings from being presented as confirmed facts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is arojit/vulnpilot-mcp's own configuration. It tells Claude Code and Codex how to work on vulnpilot-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vulnpilot-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to arojit/vulnpilot-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/arojit/vulnpilot-mcp/main/.agents/skills/oss-audit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/arojit/vulnpilot-mcp

Made for: Claude Code, Codex.

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 oss-vulnerability-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/arojit/vulnpilot-mcp/oss-audit.svg)](https://agentmods.dev/skills/arojit/vulnpilot-mcp/oss-audit)
Your own site
<a href="https://agentmods.dev/skills/arojit/vulnpilot-mcp/oss-audit"><img src="https://agentmods.dev/badge/skills/arojit/vulnpilot-mcp/oss-audit.svg" alt="Measured on agentmods" 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 690 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 $0.00690
Opus 5 $0.00023 $0.00345
Sonnet 5 $0.00009 $0.00138
Haiku 4.5 $0.00005 $0.00069

Measured 6d ago against content hash 9bec71e2ab5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

oss-vulnerability-audit 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 6d 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.

.agents/skills/oss-audit/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OSS Vulnerability Audit with VulnPilot

Use the VulnPilot MCP server tools whenever the user asks to:

  • Audit dependencies for vulnerabilities
  • Check if a package version is vulnerable
  • Analyze reachability of a dependency
  • Generate a security report
  • Perform supply-chain or OSS risk analysis

Workflow

1. Identify Dependencies

Read the project's manifest file to extract dependency names and versions:

Ecosystem Files to read
PyPI pyproject.toml, requirements.txt, uv.lock, poetry.lock
npm package.json, package-lock.json, yarn.lock
Maven pom.xml
Gradle build.gradle, build.gradle.kts

2. Check Each Package

For every dependency, call the VulnPilot check_package tool:

check_package(
    package_name="<name>",
    version="<version>",
    ecosystem="PyPI"  # or npm, Maven, Gradle
)

3. Analyze Reachability (for vulnerable packages)

For each vulnerable package, call analyze_reachability:

analyze_reachability(
    project_path="/absolute/path/to/project",
    package_name="<name>",
    ecosystem="PyPI"
)

Then re-call check_package with the reachability and scope info to refine priority:

check_package(
    package_name="<name>",
    version="<version>",
    ecosystem="PyPI",
    is_reachable=True,
    dependency_scope="production"
)

4. Generate Report

After all packages are checked, aggregate the results and call generate_report:

generate_report(
    results=[...],           # list of PackageReport objects
    project_name="my-app",
    ecosystem="PyPI",
    output_dir=".vulnpilot"
)

This produces a self-contained HTML report saved to .vulnpilot/.

5. Summarize

Present a concise summary to the user:

  • Total packages scanned vs vulnerable
  • Breakdown by priority (IMMEDIATE > URGENT > HIGH > NORMAL)
  • Top recommended actions
  • Path to the saved HTML report

Priority Levels

Priority Meaning Action
IMMEDIATE Listed in CISA KEV — actively exploited Patch today
URGENT Reachable + EPSS ≥ 50% Fix this sprint
HIGH Production + CRITICAL severity Plan for next release
NORMAL Lower risk Track and address at convenience

Read the full file on GitHub · 106 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. 6d ago First seen · 106 lines · 45 tokens per session scan A 9bec71e2ab5a

Subscribe to this mod's changes

oss-vulnerability-audit is a skill published in the GitHub repository arojit/vulnpilot-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 690 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 2026-08-31.

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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens