Directory / Claude community plugins (Anthropic) / security-watchdog
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-plugin forge@forge before proceeding." ↓ Claude runs /scan-plugin, reads all plugin files, applies security checks, and reports findings ``` The snapshot is updated on detection — each change event fires the alert exactly once.Description from the marketplace entry / plugin manifest.
Information source
Copied from the Claude community plugins (Anthropic) catalog (anthropics/claude-plugins-community), maintained by Anthropic (community submissions).
- Marketplace entry:
.claude-plugin/marketplace.json
Links are pinned to commit 06ec7b6 (2026-10-13), the version we synced. Not reviewed by us.
Install
Add the marketplace (once, in Claude Code)
/plugin marketplace add anthropics/claude-plugins-communityIn a Claude Code session
/plugin install security-watchdog@claude-communityFrom your shell
claude plugin install security-watchdog@claude-communityCommands follow each host's documentation (Claude Code, Claude Cowork docs). gh skill needs GitHub CLI 2.90 or later and is in public preview.
Listed from Anthropic (community submissions)'s catalog, not reviewed by us. Read the source before installing.
- Catalog
- Claude community plugins (Anthropic) (
claude-community) - Information source
- marketplace.json in anthropics/claude-plugins-community
- Author
- Not stated in the source
- Source code
- Entelligentsia/skillforge
- License
- MIT (repository license)
- Repository stars
- 3 for Entelligentsia/skillforge
- Added to catalog
- 2026-04-07
- Last change
- 2026-07-30 (last push to the repo)
What it contains
Hosted in an external repository, so contents are not counted here. See the source link.
Similar in Security
- claude-seo (Claude community plugin)
- rustunnel (Claude community plugin)
- very-good-ai-flutter-plugin (Claude community plugin)
- agentic-security (Claude community plugin)
- malchela (Claude community plugin)
- great-cto (Claude community plugin)