Hardening Agent Skills

Skills

• HardeningCommunity · Matt Pocock

  308.7k

  git-guardrails-claude-code

  Changes Claude Code hook settings (project or global), after which Claude can no longer run git push and the other blocked commands.

  • git
  • hooks
  • safety

  Sets up a Claude Code PreToolUse hook that blocks dangerous git commands such as push, reset --hard, clean and branch -D before they run.

  Scan passedskills

  Permissions:

  • read-repo
  • write-files
  • shell
  • network

  MIT|Claude Code, Codex, Copilot, Gemini CLI

  Preview SKILL.md
• HardeningCommunity · Affaan Mustafa

  294.3k

  agent-security-hardening

  • security
  • agents
  • hardening

  Hardens the boundaries where an agent turns untrusted data into filesystem, network, memory or tool actions, producing concrete controls and tests.

  Scan passedECC

  Permissions:

  • read-repo
  • write-files
  • shell
  • network

  MIT|Claude Code, Codex, Cursor, Copilot, OpenCode

  Preview SKILL.md
• HardeningCommunity · Garry Tan

  138.5k

  guard

  Registers hooks that block edits outside a directory; the boundary persists after the session until /unfreeze, and usage is logged to a local gstack analytics file.

  • safety
  • hooks
  • gstack

  Turns on destructive-command warnings and a directory-scoped edit boundary together, combining /careful and /freeze in one command.

  Scan passedgstack · v0.1.0

  Permissions:

  • read-repo
  • write-files
  • shell
  • network

  MIT|Claude Code, Codex, Cursor, Copilot

  Preview SKILL.md
• HardeningCommunity · Addy Osmani

  112.3k

  security-and-hardening

  • security
  • owasp
  • web

  Hardens web app code against vulnerabilities, starting from a threat model and covering input, auth, sessions, dependencies, privacy and LLM features.

  Scan passedagent-skills

  Permissions:

  • read-repo
  • write-files
  • shell
  • network

  MIT|Claude Code, Codex, Cursor, Copilot, Gemini CLI

  Preview SKILL.md
• HardeningCommunity · David Dias

  74.6k

  content-security-policy

  • csp
  • xss
  • headers

  Checks for and implements a strict Content Security Policy, combined with HTML sanitization and Trusted Types against XSS and injection.

  Scan passedFront-End-Checklist

  Permissions:

  • read-repo
  • write-files
  • shell
  • network

  MIT|Any SKILL.md agent

  Preview SKILL.md
• HardeningCommunity · Seth Hobson

  42.1k

  k8s-security-policies

  The troubleshooting commands need kubectl credentials for the target cluster.

  • kubernetes
  • security
  • rbac

  Implements defense-in-depth for Kubernetes clusters with NetworkPolicy, Pod Security Standards, RBAC, OPA Gatekeeper and Istio mTLS.

  Scan passedagents

  Permissions:

  • read-repo
  • write-files
  • shell
  • network

  MIT|Claude Code, Codex, Cursor, Copilot, OpenCode

  Preview SKILL.md

No matching skills. Adjust your keywords or switch category.