InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. SkillSpector

    Skills

    Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.

    Indexed GitHub, NVIDIA 25.9k ★Apache-2.0Updated 2 days ago

    git clone https://github.com/NVIDIA/SkillSpector.git
  2. skill-scanner

    Skills

    Security Scanner for Agent Skills

    Stale GitHub, cisco-ai-defense 2,616 ★Custom licence (see repository)Updated 27 days ago

    git clone https://github.com/cisco-ai-defense/skill-scanner.git
  3. Offline security scanner for AI-agent repos, skills, plugins, and MCP servers.

    Stale GitHub, alexgreensh 205 ★Custom licence (see repository)Updated 11 days ago

    git clone https://github.com/alexgreensh/repo-forensics.git
  4. 30 Claude Code Skills + 60+ integrated tools for HackerOne/Bugcrowd bug bounty hunters

    Stale GitHub, 0xGhostCAT 43 ★Custom licence (see repository)Updated 5 months ago

    git clone https://github.com/0xGhostCAT/claude-ai-cyber-security-skills.git
  5. Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

    Indexed GitHub, NVIDIA 1,963 ★Apache-2.0Updated today

    git clone https://github.com/NVIDIA/SkillEvaluator.git
  6. Cross-Code Organizer (formerly Claude Code Organizer): cross-harness config dashboard for Claude Code, Codex CLI, MCP servers, skills, memories, agents, sessions, security scanning, context budget, and backups.

    Stale GitHub, mcpware 386 ★MITUpdated 17 days ago

    git clone https://github.com/mcpware/cross-code-organizer.git
  7. Security scanner for Claude Code Skills — 9 engines detect malicious patterns, data exfiltration, dangerous ops across 71K+ skills

    Stale GitHub, claude-world 83 ★MITUpdated 15 days ago

    git clone https://github.com/claude-world/claude-skill-antivirus.git
  8. saferskills

    Skills

    Every AI skill, independently scanned. Public, open-source trust scoring for skills, MCP servers, hooks, and plugins across every agent platform. Apache-2.0. saferskills.ai

    Stale GitHub, OpenLatch 9 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/OpenLatch/saferskills.git
  9. skillhawk

    Skills

    Catch dangerous AI agent skills before they catch you. Zero-dependency security scanner for Agent Skills, SKILL.md and MCP configs.

    Indexed GitHub, Berserk-hub150 70 ★MITUpdated 3 days ago

    git clone https://github.com/Berserk-hub150/skillhawk.git
  10. skillguard

    Skills

    Security scanner for AI agent skills. Detects prompt injection, data exfiltration, and malicious payloads before you install.

    Stale GitHub, obielin 20 ★Custom licence (see repository)Updated 24 days ago

    git clone https://github.com/obielin/skillguard.git
  11. SkillsGuard

    Skills

    Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts before they run.

    Stale GitHub, Teycir 15 ★Updated 14 days ago

    git clone https://github.com/Teycir/SkillsGuard.git
  12. vibe-shield

    Skills

    92-rule static security scanner, Agent Skill & MCP server for AI-generated Next.js, Supabase & TypeScript apps (OWASP Top 10:2025 + MCP/Skill poisoning).

    Indexed GitHub, avivgerz-hue 45 ★MITUpdated yesterday

    git clone https://github.com/avivgerz-hue/vibe-shield.git

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.