內容簡介
<h3>Summary:</h3>
<ul>
<li>SpamAnvil 是一款免費、開源的 WordPress 反垃圾郵件外掛程式，利用人工智慧技術來阻擋評論垃圾郵件。</li>
<li>與 Akismet 不同，SpamAnvil 使用大規模語言模型 (LLMs) 理解評論並檢測最複雜的垃圾郵件。</li>
<li>適用於免費 AI 模型，保證隱私，支持多家 AI 提供者。</li>
</ul>
<h3>Questions and Answers:</h3>
<h4>Why should I choose SpamAnvil?</h4>
<p>SpamAnvil is 100% free with no hidden costs, smarter than rule-based filters, and understands context better. It works with free AI models and respects your privacy.</p>
<h4>What are some key features of SpamAnvil?</h4>
<p>Key features include AI-powered spam detection, intelligent heuristics engine, async background processing, smart IP blocking, encrypted API key storage, customizable AI prompts, and a statistics dashboard.</p>
<h4>How does SpamAnvil work against spam comments?</h4>
<p>When a visitor submits a comment, SpamAnvil checks for blocked IPs, runs a pre-analysis, and queues for AI analysis. If a comment is marked as spam by the AI, it gets blocked. Repeat offender IPs are also automatically blocked.</p>
<h4>What are some use cases for SpamAnvil?</h4>
<p>SpamAnvil is ideal for blogs receiving lots of spam comments, WooCommerce stores concerned about SEO, membership sites safeguarding community discussions, and multilingual sites needing AI support.</p>
外掛標籤
開發者團隊
📦 歷史版本下載
原文外掛簡介
SpamAnvil is a free, open-source WordPress anti-spam plugin that uses artificial intelligence to block comment spam. Unlike Akismet (which requires a paid plan for commercial sites) or simple keyword-based filters, SpamAnvil leverages large language models (LLMs) to actually understand your comments and detect even the most sophisticated spam.
Traditional spam filters rely on static word lists and link counting. Spammers have evolved. SpamAnvil fights back with AI that understands context, intent, and language patterns – catching spam that looks legitimate and approving real comments that others would flag.
Why SpamAnvil?
100% Free – No premium tier, no subscription, no hidden costs. Bring your own API key (free options available).
Smarter Than Rules – AI understands context. A comment about “buying a new home” won’t be flagged just because it contains “buy”.
Works With Free AI Models – Use OpenRouter’s free Llama models for $0 cost, or connect premium models for maximum accuracy.
Privacy-First – Your data stays between you and your chosen AI provider. IP addresses are stored as irreversible SHA-256 hashes. GDPR/LGPD compliant by design.
No Cloud Lock-in – Choose from 6+ AI providers. Switch anytime. Your anti-spam, your rules.
Supported AI Providers
OpenAI (GPT-4o-mini, GPT-4o, etc.)
Anthropic Claude (Claude Sonnet, Haiku, etc.)
Google Gemini (Gemini 2.0 Flash, Pro, etc.)
OpenRouter (100+ models, including FREE ones)
Featherless.ai (Open-source models)
Any OpenAI-compatible API (LM Studio, Ollama via proxy, vLLM, etc.)
Key Features
AI-Powered Spam Detection – Each comment is analyzed by an LLM that scores it 0-100 for spam probability
Intelligent Heuristics Engine – Pre-analyzes comments with regex patterns, spam word detection, URL counting, and prompt injection detection to catch obvious spam without API calls
Async Background Processing – Comments are queued and processed via WP-Cron so your site stays fast
Smart IP Blocking – Automatically blocks repeat offenders with escalating ban durations (24h, 48h, 96h…)
Automatic Retry with Backoff – Failed API calls retry up to 3 times with exponential delays
Encrypted API Key Storage – AES-256-CBC encryption for all stored API keys. Optional wp-config.php constants for maximum security
Statistics Dashboard – Track how many comments were checked, how much spam was caught, API usage and errors
Full Evaluation Logs – See the AI’s reasoning for every comment scored, with provider, model, response time, and score
Customizable AI Prompts – Full control over what the AI is instructed to do
Fallback Provider – Configure a backup AI so spam checking never stops
Prompt Injection Defense – Multi-layered protection prevents attackers from manipulating the AI through crafted comments
Configurable Spam Threshold – Slide between aggressive (catch more spam) and permissive (fewer false positives)
Moderator Bypass – Trusted users skip spam checking entirely
How It Works
A visitor submits a comment
SpamAnvil checks if the IP is blocked from previous spam attempts
The heuristic engine runs a quick pre-analysis (URL count, spam words, suspicious patterns)
If the heuristic score is very high, the comment is instantly marked as spam – no API call needed
Otherwise, the comment is queued for AI analysis (or processed immediately in sync mode)
The AI analyzes the comment in context (post title, author info, heuristic data) and returns a spam score
Comments scoring above your threshold are marked as spam; clean comments are auto-approved
Repeat offender IPs are automatically blocked with escalating durations
Use Cases
Blogs receiving hundreds of spam comments per day
WooCommerce stores where comment spam affects SEO and credibility
Membership sites that need to protect community discussions
Multilingual sites – AI understands comments in any language, unlike keyword-based filters
High-traffic sites – Async processing handles any volume without slowing down your site
Sites tired of Akismet – Free alternative with no cloud dependency and full data control
Security
SpamAnvil follows WordPress security best practices throughout:
AES-256-CBC encrypted API key storage
wp-config.php constant support for API keys (never touch the database)
Nonce verification on all forms and AJAX requests
Capability checks on all admin actions
Prepared SQL statements on every database query
Output escaping on all rendered content
Prompt injection defense: boundary tags, system prompt hardening, heuristic injection detection, strict JSON validation, temperature 0
Languages
English (default)
Translation-ready (.pot file included)
Third-Party Services
SpamAnvil sends comment data (content, author name, email, and URL) to external AI services for spam analysis. The specific service used depends on your configuration. No data is sent until you configure and enable a provider.
OpenAI — https://openai.com — Terms of Use — Privacy Policy
Anthropic (Claude) — https://www.anthropic.com — Terms of Service — Privacy Policy
Google Gemini — https://ai.google.dev — Terms of Service — Privacy Policy
OpenRouter — https://openrouter.ai — Terms of Service — Privacy Policy
Featherless.ai — https://featherless.ai — Terms of Service — Privacy Policy
When using the “Generic OpenAI-Compatible” option, data is sent to the URL you configure. You are responsible for ensuring compliance with the privacy policies of your chosen service.
