security-watchdog
Developer not provided
> 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...
From the developer
Works with
Claude Code
Description
From the marketplace listing
> 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.
What changed
No changes recorded yet. Follow this plugin to keep track of future changes.
Similar plugins
Find competitors to follow as you develop your plugin.
-
Security audit plugin that scans Claude Code skills, hooks, and MCP configurations for threats. Detects 37 attack patterns including prom...
Shared terms: detect, exfiltration, injection, scan
-
Frictionless security, compliance, and threat detection for Claude Code and Co-Work. Advanced Behavioral detection patterns catch credent...
Shared terms: exfiltration, injection, prompt, security
-
Real-time security filter for MCP tool communications. Works as a Claude Code hook to inspect all data sent to and received from MCP serv...
Shared terms: detect, injection, prompt, hook
-
LLM security for AI coding agents. Protect applications from prompt injection, PII leakage, and data exfiltration. Provides MCP tools for...
Shared terms: exfiltration, injection, prompt, security
-
Skill Safety Auditor is a Claude Code skill that audits third-party skills for security risks before or after you install them. It runs 1...
Shared terms: injection, prompt, security, code
Files & skills
security-watchdog · catalog manifest
Saved declaration
{}
security-watchdog · catalog manifest
Saved declaration
{
"name": "security-watchdog",
"source": {
"ref": "main",
"sha": "1abfa8b6f22d3116b6ccd0147fbeb217b06f7e38",
"url": "Entelligentsia/skillforge",
"path": "security-watchdog",
"source": "git-subdir"
},
"homepage": "https://entelligentsia.in/open-source/skillforge",
"description": "> 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.\n\n## The Problem\n\nLLM extension ecosystems are a novel attack surface. Traditional security tooling does not cover two threats unique to AI extensions:\n\n- **Host attacks** — hook scripts run shell commands automatically on session start, with full user privileges\n- **Mind attacks** — skill and command files are injected directly into the model's reasoning context, enabling prompt injection\n\nNo existing security scanner understands these threat classes. Security Watchdog is purpose-built for them.\n\n## How It Works\n\n```\nYou run: /plugin install someone/new-plugin\n↓\nNext session starts (SessionStart hook fires)\n↓\ncheck-new-plugins.sh diffs installed_plugins.json\nagainst a snapshot from the previous session\n↓\nNew/updated plugin detected\n↓\nInjects into session context:\n\"SECURITY WATCHDOG ALERT: forge@forge was installed.\nRun /scan-plugin forge@forge before proceeding.\"\n↓\nClaude runs /scan-plugin, reads all plugin files,\napplies security checks, and reports findings\n```\n\nThe snapshot is updated on detection — each change event fires the alert exactly once."
}
Catalog declarations and available plugin.json metadata are saved. Referenced skills and executable source files are not downloaded or tested. Missing components in a manifest do not prove that the plugin has none.
Installation instructions
Community
/plugin marketplace add anthropics/claude-plugins-community
/plugin install security-watchdog@claude-communityTechnical details
- Sources
- Community
- First seen
- Oct 3, 2026 · 22:13 UTC
- Last seen
- Nov 7, 2026 · 00:08 UTC
- Latest observed change
- Oct 3, 2026 · 22:13 UTC
- Collection status
- Listed
- Reported installs
- Not provided
Installation counts are source-reported, not independently verified active users. Observation dates are not release dates.
Download plugin data (JSON)Plugin history: freshly prepared. Prepared . Refreshed when catalog data changes or after 6 hours. Your account and Follow status are live.