security-watchdog vs AgentGuard — security checks for AI agents
security-watchdog is a plugin bundle for AI coding tools published by Entelligentsia. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). AgentGuard — security checks for AI agents is an MCP server published by shuaicongxiaomai. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-11-10. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |  security-watchdog |  AgentGuard — security checks for AI agents |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 0.1.0 Forks (GitHub): 1 Stars (GitHub): 3 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 0.1.2 Forks (GitHub): 0 Stars (GitHub): 0 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | security-watchdog | AgentGuard — security checks for AI agents |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 3 (better) | 0 (worse) |
| Forks (GitHub) (differs) | 1 (better) | 0 (worse) |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | On your machine (ghcr.io/shuaicongxiaomai/agentguard:0.1.2) |
| Transport (differs) | Not stated | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for | Not published | Not published |
| Hooks it runs (differs) | 1 | Not published |
| Parts of the bundle (differs) | 3 | Not a bundle |
| Licence (differs) | MIT | Not stated |
| Repository (differs) | github.com/entelligentsia/skillforge | github.com/shuaicongxiaomai/agentguard |
| Changes in the last 7 days | 0 | 0 |
| First seen | 2026-10-11 | 2026-10-11 |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
security-watchdog
> Automatic security scanner for Claude Code plugins — detects new or updated extensions at session start and scans them for prompt injection, malicious hook scripts, and data exfiltration. ## The Problem LLM extension ecosystems are a novel attack surface. Traditional security tooling does not cover two threats unique to AI extensions: - **Host attacks** — hook scripts run shell commands automatically on session start, with full user privileges - **Mind attacks** — skill and command files are injected directly into the model's reasoning context, enabling prompt injection No existing security scanner understands these threat classes. Security Watchdog is purpose-built for them. ## How It Works ``` You run: /plugin install someone/new-plugin ↓ Next session starts (SessionStart hook fires) ↓ check-new-plugins.sh diffs installed_plugins.json against a snapshot from the previous session ↓ New/updated plugin detected ↓ Injects into session context: "SECURITY WATCHDOG ALERT: forge@forge was installed. Run /scan-plu
AgentGuard — security checks for AI agents
Secret, CVE and dependency-vulnerability scanning for AI agents (free, OSV.dev).
How to run each
security-watchdog As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install security-watchdog@claude-communityAgentGuard — security checks for AI agents As a local MCP server: Docker image
claude mcp add --transport stdio agentguard -- docker run -i --rm ghcr.io/shuaicongxiaomai/agentguard:0.1.2Commands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
Neither one's marketplaces publish the settings it asks for.
What it can do: security-watchdog · What it can do: AgentGuard — security checks for AI agents · Compare two other plugins
Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.