security-scan

security-scan is a command for coding agents from harish-garg/security-scanner-plugin. It costs 12 tokens per session (1,194 once invoked), scanned A, original, MIT.

A repository security audit that combines checks for unsafe dependencies, code problems, and exposed secrets. Dependabot is GitHub's service for finding vulnerable software packages.

In plain words
What is it for?
Use it to inspect a GitHub repository for dependency vulnerabilities, code-scanning findings, and leaked credentials.
Why use it?
It collects several kinds of security alerts in one report and groups them by severity, so important issues are easier to review.

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/security-scan
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 security-scan

README.md
[![agentmods](https://agentmods.dev/badge/commands/harish-garg/security-scanner-plugin/security-scan.svg)](https://agentmods.dev/commands/harish-garg/security-scanner-plugin/security-scan)
Your own site
<a href="https://agentmods.dev/commands/harish-garg/security-scanner-plugin/security-scan"><img src="https://agentmods.dev/badge/commands/harish-garg/security-scanner-plugin/security-scan.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,194 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00012 $0.01194
Opus 5 $0.00006 $0.00597
Sonnet 5 $0.00002 $0.00239
Haiku 4.5 $0.00001 $0.00119

Measured 3d ago against content hash b267c26af55c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-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 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.

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.

commands/security-scan.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Scan

Run a full security audit of the current repository combining dependency, code, and secret scanning.

What to do:

  1. Identify repository: Determine the current repository (owner/repo) from Git configuration

    • Use git remote -v or check .git/config to find the repository
    • Parse owner and repo name from GitHub URL
  2. Run comprehensive security checks (in parallel if possible):

    a) Dependency vulnerabilities: Use GitHub MCP's list_dependabot_alerts

    • Parameters: owner, repo, state: "open"
    • Collect: CVE IDs, severity, affected packages, fix versions

    b) Code security issues: Use GitHub MCP's list_code_scanning_alerts

    • Parameters: owner, repo, state: "open"
    • Collect: Rule IDs, severity, locations, descriptions

    c) Secret exposure: Use GitHub MCP's list_secret_scanning_alerts

    • Parameters: owner, repo, state: "open"
    • Collect: Secret types, locations (NEVER actual values)
  3. Aggregate and analyze all findings:

    • Combine all alerts across all three scan types
    • Group by severity: Critical, High, Medium, Low
    • Sort by severity and impact
    • Calculate total vulnerability count
  4. Present comprehensive security report:

    ═══════════════════════════════════════════════════════
    Security Audit Report for owner/repo
    ═══════════════════════════════════════════════════════
    
    📊 Executive Summary:
    Total security issues: X
    - Critical: X
    - High: X
    - Medium: X
    - Low: X
    
    ═══════════════════════════════════════════════════════
    🔴 Critical & High Priority Issues
    ═══════════════════════════════════════════════════════
    
    [Dependency Vulnerabilities]
    1. package-name@version - CVE-XXXX-XXXX (Critical)
       Type: [Vulnerability type, e.g., Remote Code Execution]
       Impact: [What could happen]
       Fix: npm install [email protected]
       Details: /explain-cve CVE-XXXX-XXXX
    
    2. another-package@version - CVE-YYYY-YYYY (High)
       Type: [Vulnerability type]
       Impact: [What could happen]
       Fix: yarn upgrade another-package@^X.X.X
    
    [Code Security Issues]
    3. [Rule name] detected (High)
       Location: src/file.js:42
       Issue: [Brief description]
       Recommendation: [How to fix]
    
    [Exposed Secrets]
    4. AWS Access Key exposed (Critical)
       Location: config/settings.yml
       ⚠️  IMMEDIATE ACTION REQUIRED: Revoke and rotate credential
    
    [Show top 5-10 most critical across all categories]
    
    ═══════════════════════════════════════════════════════
    📋 Breakdown by Category
    ═══════════════════════════════════════════════════════
    
    🔧 Dependencies: X issues
    💻 Code Security: X issues
    🔒 Exposed Secrets: X issues
    
    ═══════════════════════════════════════════════════════
    ✅ Recommended Actions (Prioritized)
    ═══════════════════════════════════════════════════════
    
    **Immediate (Critical):**
    1. Revoke exposed AWS key and rotate credentials
    2. Update package-name to fix CVE-XXXX-XXXX (RCE vulnerability)
    3. [Other critical items]
    
    **High Priority (This Week):**
    1. Fix [code security issue] in src/file.js
    2. Update [high-severity dependencies]
    3. [Other high priority items]
    
    **Medium Priority (This Sprint):**
    1. Address remaining dependency updates
    2. Review and fix code scanning alerts
    3. [Other medium priority items]
    
    **Low Priority (Backlog):**
    1. [Low severity items]
    
    ═══════════════════════════════════════════════════════
    🔗 Additional Resources
    ═══════════════════════════════════════════════════════
    
    - Full Dependabot alerts: https://github.com/owner/repo/security/dependabot
    - Code scanning alerts: https://github.com/owner/repo/security/code-scanning
    - Secret scanning alerts: https://github.com/owner/repo/security/secret-scanning
    
    💡 Next Steps:
    - Use /explain-cve [CVE-ID] for detailed vulnerability explanations
    - Use /check-deps for quick dependency-only checks
    - Use /check-secrets to focus on credential exposure
    - Review GitHub Security tab for complete details
    

Read the full file on GitHub · 134 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 · 134 lines · 12 tokens per session scan A b267c26af55c

Subscribe to this mod's changes

security-scan is a command published in the GitHub repository harish-garg/security-scanner-plugin (9 stars, last pushed 10mo ago), licensed MIT. It adds 12 tokens to every session and 1,194 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 2026-08-31.