explain-cve

explain-cve is a command for coding agents from harish-garg/security-scanner-plugin. It costs 10 tokens per session (591 once invoked), scanned B, original, MIT.

A command that explains a CVE, which is a public identifier for a specific software security vulnerability, in everyday language. It can check whether the issue affects the current repository.

In plain words
What is it for?
Use it with a CVE identifier or vulnerability name to understand what could happen and how to address it.
Why use it?
It turns technical vulnerability details into an explanation of the risk, affected versions, fixes, and practical next steps.

Command

Part of the github-security-scanner plugin — 4 commands, 1 agent shipped together

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.

agentmods
npx agentmods add commands/harish-garg/security-scanner-plugin/explain-cve
Clone the repo
git clone --depth 1 https://github.com/harish-garg/security-scanner-plugin

Or install github-security-scanner, the plugin that ships this one along with the rest of its 4 commands, 1 agent.

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 explain-cve

README.md
[![agentmods](https://agentmods.dev/badge/commands/harish-garg/security-scanner-plugin/explain-cve.svg)](https://agentmods.dev/commands/harish-garg/security-scanner-plugin/explain-cve)
Your own site
<a href="https://agentmods.dev/commands/harish-garg/security-scanner-plugin/explain-cve"><img src="https://agentmods.dev/badge/commands/harish-garg/security-scanner-plugin/explain-cve.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 591 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00010 $0.00591
Opus 5 $0.00005 $0.00296
Sonnet 5 $0.00002 $0.00118
Haiku 4.5 $0.00001 $0.00059

Measured 3d ago against content hash 1cc8ff243492, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

explain-cve scanned grade B with 1 finding 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 3d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

This vulnerability allows attackers to inject and execute arbitrary commands
commands/explain-cve.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Explain CVE

Help users understand what a specific vulnerability means and how to fix it.

Usage

This command can be used in two ways:

  1. With CVE argument: /explain-cve CVE-2021-23337
  2. Interactive: /explain-cve (will prompt for CVE)

What to do:

  1. Extract CVE from arguments: Check if user provided CVE/vulnerability ID after the command

    • If provided, use that CVE identifier directly
    • If not provided, ask for the CVE identifier or vulnerability name
  2. Identify repository context: Determine the current repository (owner/repo) from the working directory

  3. Gather information:

    • Use GitHub MCP's list_dependabot_alerts to check if this CVE affects the current repo
    • If found, use get_dependabot_alert to get detailed information
    • If not found in current repo, provide general CVE information
  4. Explain in plain English:

    • What it is: Brief description of the vulnerability type (e.g., "SQL Injection", "Command Injection")
    • Impact: What could happen if exploited (e.g., "Remote Code Execution", "Data Exposure")
    • Affected versions: Which package versions are vulnerable
    • Fixed versions: Which versions include the fix
    • How to fix: Specific upgrade commands and steps
    • Workarounds: Temporary mitigations if upgrade isn't immediately possible
    • Risk level: Severity rating with context for this specific project

Example Output Format

CVE-2021-23337 - Command Injection in lodash

What it is:
This vulnerability allows attackers to inject and execute arbitrary commands
through lodash template strings. The issue occurs when user-controlled input
is processed by lodash's template function without proper sanitization.

Impact: 🔴 Critical - Remote Code Execution
Attackers can execute arbitrary code on your server if your application
processes user input through lodash templates.

Affected versions: lodash < 4.17.21
Fixed in: lodash 4.17.21 and later

How to fix:
npm install lodash@latest
or
yarn upgrade lodash@^4.17.21

Workaround (if immediate upgrade not possible):
Avoid using lodash template() with user-controlled input, or implement
strict input validation before processing.

Status in this repository:
✅ Not affected - you're using [email protected]
OR
⚠️ Vulnerable - found in package.json ([email protected])

Read the full file on GitHub · 70 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. 3d ago First seen · 70 lines · 10 tokens per session scan B 1cc8ff243492

Subscribe to this mod's changes

explain-cve is a command published in the GitHub repository harish-garg/security-scanner-plugin (9 stars, last pushed 10mo ago), licensed MIT. It adds 10 tokens to every session and 591 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.