Auto-scans newly installed Claude Code plugins for prompt injection, malicious hook scripts, and data exfiltration
Plugin security-watchdog from marketplace skillforge in Entelligentsia/skillforge. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
plugin-securityLLM extension security analysis — threat model, attack patterns, and heuristics for evaluating Claude Code plugins and skills for prompt injection, hook script abuse, permission escalation, and data exfiltration. Load when reviewing any LLM extension, skill pack, or agent for security.
/security-watchdog:scan-pluginSecurity scan a specific installed Claude Code plugin for prompt injection, malicious hooks, data exfiltration, and permission abuse
node "${CLAUDE_PLUGIN_ROOT}/hooks/check-new-plugins.js"
Problems found in this repo's manifests
13 skills for agent harness components — memory/compaction, session persistence, prompt caching, subagent orchestration, sandboxing, permissions, streaming, concurrency, telemetry, hooks, workspace state, model routing, rate limiting
13 skills
Commit-time clean-code review gate — blocks unreviewed commits, reviews the staged diff against a layered rubric, and resolves findings through a single apply/manual/approve decision; silent when there is nothing to report
4 skills · 4 commands · 1 agent · hooks
10 skills covering all 23 GoF patterns plus enterprise and DDD patterns
10 skills
9 skills for LLM integration patterns — RAG, tool use, agents, guardrails, tool synthesis
10 skills
10 skills for Three.js 3D development
10 skills
8 skills for Meta Quest PWA XR engineering
8 skills
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.
hooks
Cross-installation agent federation with zero-trust security, PII-gated data flow, and compliance-grade audit trails
3 skills · 1 command · 1 agent
Install the "AAS Security Engineer" workflow plugin from Agentic Awesome Skills.
12 skills
Duende development skills and agents for Claude Code — covering OAuth/OIDC protocols, IdentityServer, token management, ASP.NET Core authentication/authorization, BFF patterns, and secure identity architecture
24 skills · 2 agents
SAST analysis, dependency vulnerability scanning, OWASP Top 10 compliance, container security scanning, and automated security hardening
5 skills · 3 commands · 2 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.