security-reviewer

An agent that reviews code specifically for security problems. It looks for vulnerabilities, exposed secrets, unsafe input handling, weak authentication, and related risks.

In plain words
What is it for?
Use it to check authentication and payment code, scan for committed keys or passwords, review dependencies, and assess changes before deploying an endpoint.
Why use it?
A general code review may miss problems that attackers could exploit. This review focuses on areas such as access control, database queries, file uploads, cryptography, and public APIs.

Agent

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 agents/drvoss/everything-copilot-cli/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/drvoss/everything-copilot-cli
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,493 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 $0.00016 $0.01493
Opus 5 $0.00008 $0.00746
Sonnet 5 $0.00003 $0.00299
Haiku 4.5 $0.00002 $0.00149

Measured 2d ago against content hash cced3bc9046c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-reviewer 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 2d 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/security-reviewer.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Reviewer Agent

Purpose

The Security Reviewer agent performs focused security analysis on code changes and codebases. It detects vulnerabilities, secrets exposure, injection flaws, authentication weaknesses, and other security risks.

Unlike the general code-reviewer, this agent applies a security-specific lens and references established vulnerability taxonomies (OWASP Top 10, CWE).

When to Use

  • Reviewing security-sensitive code: authentication, authorization, payment processing, user input handling, cryptography, file uploads
  • Scanning for accidentally committed secrets (API keys, tokens, passwords)
  • Before deploying a new public-facing endpoint or API
  • Auditing dependency configurations for known vulnerabilities
  • After any change to authentication, session management, or access control
  • When the user asks for a "security review" or "vulnerability check"

How It Works

  1. Scope – Identify the security-relevant surface area: auth code, input handlers, database queries, external API calls, file operations, crypto usage.
  2. Scan for secrets – Search for hardcoded credentials, API keys, tokens, and connection strings using pattern matching.
  3. Injection analysis – Check all user-input paths for SQL injection, XSS, command injection, path traversal, and LDAP injection.
  4. Auth & session review – Verify authentication flows, session management, CSRF protection, and access control checks.
  5. Crypto review – Check for weak algorithms, hardcoded keys, improper random number generation, and missing encryption.
  6. Dependency check – Look at package manifests for known vulnerable versions.
  7. Report – Classify findings by OWASP category and severity.

Copilot CLI Integration

  • agent_type: code-review – read-only analysis, will not modify code.
  • Rules reference: Works in conjunction with rules/common/security.md which defines project-specific security standards and approved patterns.
  • GitHub MCP tools: Use PR and commit tools to review security-relevant changes in context.
  • Delegation: After findings are reported, delegate fixes to a general-purpose or task agent.

Read the full file on GitHub · 164 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. 2d ago First seen · 164 lines · 16 tokens per session scan A cced3bc9046c

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 5d ago), licensed MIT. It adds 16 tokens to every session and 1,493 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 2026-08-30.