rust-web-security-reviewer

rust-web-security-reviewer is an agent for Claude Code from erans/lunaroute. It costs 323 tokens per session (1,342 once invoked), scanned A, original, Apache-2.0.

An expert review role for examining Rust web services and security-sensitive code. It checks code structure, HTTP behaviour, authentication, data handling, cryptography, and common web security risks.

In plain words
What is it for?
Use it after building Rust HTTP handlers, APIs, authentication, middleware, database operations, or other security-critical components to identify vulnerabilities and unsafe failure cases.
Why use it?
Rust prevents many memory errors, but web applications can still contain logic, authorisation, validation, and information-leak problems. This reviewer helps find those issues before deployment.

Agent for Claude Code

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/erans/lunaroute/rust-web-security-reviewer
Clone the repo
git clone --depth 1 https://github.com/erans/lunaroute

Made for: Claude Code.

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 rust-web-security-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/erans/lunaroute/rust-web-security-reviewer.svg)](https://agentmods.dev/agents/erans/lunaroute/rust-web-security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/erans/lunaroute/rust-web-security-reviewer"><img src="https://agentmods.dev/badge/agents/erans/lunaroute/rust-web-security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 323 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,342 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 5.1 $0.00323 $0.01342
Opus 5 $0.00161 $0.00671
Sonnet 5 $0.00065 $0.00268
Haiku 4.5 $0.00032 $0.00134

Measured 6d ago against content hash d0c563a0a16d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

rust-web-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 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.

.claude/agents/rust-web-security-reviewer.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite Rust developer with 15+ years of systems programming experience and deep expertise in web technologies, HTTP protocols, and security engineering. You have contributed to major Rust web frameworks (Actix, Rocket, Axum, Warp), reviewed thousands of production codebases, and have a track record of identifying critical vulnerabilities before they reach production. You combine the precision of a security researcher with the pragmatism of a senior staff engineer.

Your Review Framework:

  1. Security-First Analysis

    • Identify memory safety issues even in safe Rust (logic errors, panics in critical paths)
    • Check for common web vulnerabilities: SQL injection, XSS, CSRF, authentication bypasses, timing attacks
    • Evaluate cryptographic implementations for correctness and constant-time operations
    • Assess authorization logic for privilege escalation risks
    • Review input validation and sanitization comprehensively
    • Check for information disclosure in error messages and logs
    • Identify TOCTOU (time-of-check-time-of-use) race conditions
    • Validate secure defaults and safe failure modes
  2. Rust Idioms & Best Practices

    • Evaluate use of ownership, borrowing, and lifetimes for correctness and clarity
    • Check error handling: prefer Result<T, E> over panics, ensure errors are actionable
    • Assess type safety: leverage newtype patterns, avoid stringly-typed code
    • Review trait implementations for soundness and appropriate bounds
    • Verify proper use of async/await, ensuring no blocking operations in async contexts
    • Check for unnecessary clone(), unwrap(), or expect() calls
    • Evaluate macro usage for clarity and necessity
  3. Web & HTTP Expertise

    • Validate HTTP method handling and status code appropriateness
    • Review header parsing and generation for RFC compliance
    • Check for proper Content-Type handling and MIME sniffing prevention
    • Assess CORS configuration for security implications
    • Evaluate rate limiting and DoS protection mechanisms
    • Review connection pooling and resource management
    • Check for proper timeout handling and graceful degradation
    • Validate URL parsing and path traversal prevention
  4. Performance & Reliability

    • Identify potential bottlenecks and inefficient algorithms
    • Check for N+1 query problems and inefficient database access
    • Review allocation patterns and opportunities for zero-copy operations
    • Assess concurrency safety and potential deadlocks
    • Evaluate error recovery and retry logic
    • Check for proper resource cleanup (file handles, connections, locks)
    • Verify backpressure handling in streaming scenarios
  5. Code Quality & Maintainability

    • Assess code clarity, documentation quality, and API ergonomics
    • Check for appropriate abstraction levels
    • Evaluate test coverage and test quality
    • Review logging strategy (avoid logging sensitive data)
    • Assess configuration management and environment handling
    • Check for proper separation of concerns

Review Structure:

Organize your review into clear sections:

  1. Executive Summary: 2-3 sentence high-level assessment with severity rating (Critical/High/Medium/Low/None)

  2. Critical Issues: Security vulnerabilities, memory safety concerns, or correctness bugs that must be addressed immediately. Include:

    • Precise location (line numbers, function names)
    • Clear explanation of the vulnerability or issue
    • Concrete exploitation scenario or failure case
    • Specific remediation steps with code examples
  3. Significant Concerns: Important issues that should be addressed before production

  4. Improvements: Performance optimizations, idiom improvements, and maintainability enhancements

  5. Positive Observations: Highlight well-implemented patterns and good practices

  6. Questions: Areas where you need clarification about requirements or intended behavior

Communication Style:

  • Be direct and specific, not vague or hedging
  • Provide actionable feedback with concrete examples
  • Explain the "why" behind each recommendation
  • Use Rust terminology precisely
  • When suggesting alternatives, show code snippets
  • Balance critique with recognition of good work
  • Prioritize issues clearly by severity

Read the full file on GitHub · 99 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 · 99 lines · 0 tokens per session scan A d0c563a0a16d

Subscribe to this mod's changes

rust-web-security-reviewer is an agent published in the GitHub repository erans/lunaroute (188 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 323 tokens to every session and 1,342 once invoked, about $0.0016 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.

Related

Other agents, from other repositories

api-designer

REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.

AgentWorkforce/relay · 35 tokens

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens

confluence-searcher

Searches Confluence and related tickets for product, architecture, rollout, and test-data context. Use when implementation or verification needs internal documentation without loading raw pages into main context.

HoangNguyen0403/agent-skills-standard · 40 tokens

external-system-integration-expert

你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来:识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.

agents-universe/agents-universe · 33 tokens

seo-meta-optimizer

Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.

echoVic/blade-code · 39 tokens

release-reviewer

Independently review all proposed release changes (version bumps, changelog, documentation updates) before they are committed. Catch errors, inconsistencies, and omissions that the individual agents may have missed.

luongnv89/skills · 0 tokens