claude

mcp-security

Security auditing for MCP servers (RCE, STDIO injection, supply chain) and for GitHub Actions workflows that run Gemini CLI (untrusted-input routing, tool allowlists, credential exposure).

1 on GitHubApache-2.0updated 9 days ago
/

Plugin mcp-security from marketplace agent-skills in ghchinoy/agent-skills. Commands read from the repo's manifest — 8 days ago.

What it installs

Skills (2)

  • geminicli-github-action-review

    Reviews and hardens GitHub Actions workflows that run Gemini CLI via google-github-actions/run-gemini-cli (dispatch/invoke/review/triage patterns) against prompt injection from untrusted issue, comment and PR text, ungated triggers, ineffective tool allowlists, subagent bypass, and over-privileged G

  • mcp-auditor

    Audits local Model Context Protocol (MCP) server configurations and custom-built MCP servers for Remote Command Execution (RCE) and supply chain vulnerabilities, specifically focusing on STDIO transport injection and malicious prompt injection. Use when auditing MCP server configs, reviewing MCP ser

View source on GitHub ghchinoy.github.io

More from ghchinoy/agent-skills

All 16 plugins →

repo-authoring

claude

Repository management skills for technical writing, arXiv/Syntaxis academic preprints, editorial report artifacts, README generation, changelog curation, and commit recaps.

9 skills

1

ai-pop

claude

Virtual music artist production suite: lore planning, audio synthesis, visual design, web player compilation, and public endpoint deployment.

6 skills

1

gcp-management

claude

Google Cloud Platform and Firebase project assessment, itemized BigQuery spend analysis, quota governance, and consolidation skills.

4 skills

1

macos-hig

claude

macOS Human Interface Guidelines assistance and code reviewers for layout, interactions, and HIG compliance.

3 skills

1

scion-platform

claude

Scion platform administration, Hub bootstrap and GCE reconciliation, authorization and broker quota diagnostics, zero-downtime agent token re-minting, fleet model assessment, live model patching, and server lifecycle operations.

3 skills

1

automation-governance

claude

Frameworks and tooling for evaluating AI automation readiness (Google DeepMind Intelligent AI Delegation) and auditing AI agents against W3C User Agent fiduciary duties (Protection, Honesty, Loyalty).

2 skills

1

Maintain mcp-security?

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.

claude & codex plugins16 plugins