Public catalog
security
19 shown. Search ranks against problem language; browsing defaults to stronger public signals.
Anthropic Sandbox Runtime (srt)
An AI agent or local MCP server executes arbitrary shell commands and you need to block reads of SSH keys and confine writes to the workspace without building a container
Verified 2026-08-10
Bubblewrap
sandbox an untrusted command with a minimal filesystem and no network
Verified 2026-08-10
Claude Code Security Reviewer
Pull requests merge without any security review because the team has no dedicated appsec bandwidth
Verified 2026-08-10
Defending Code Reference Harness
You want Claude to autonomously find, execution-verify, deduplicate, and report memory-safety bugs in a C or C++ codebase using ASAN in a gVisor sandbox
Verified 2026-08-10
Encrypted DNS Server (DNSCrypt)
You operate your own recursive resolver and want clients to reach it over an encrypted DNS transport rather than exposing queries in plaintext on the local network.
Verified 2026-08-10
GhidraMCP
You are reverse engineering a binary in Ghidra for security research or malware analysis and want an LLM to decompile, analyze, and rename functions autonomously instead of pasting decompiler output into a chat window.
Verified 2026-08-10
Gitleaks
scan Git history and working trees for leaked credentials before push
Verified 2026-08-10
HashiCorp Vault
broker short-lived secrets and encryption operations behind identity policies
Verified 2026-08-10
Infisical
centralize application secrets with environment and project access controls
Verified 2026-08-10
Just the Browser
You want to disable built-in AI assistants, sponsored shortcuts, and product integrations in Chrome, Edge, Firefox, or Brave without switching browsers
Verified 2026-08-10
Microsoft Presidio
detect and redact personal data before sending text to an LLM
Verified 2026-08-10
mitmproxy
capture and compare HTTP traffic across a proxy or client boundary
Verified 2026-08-10
NVIDIA NeMo Guardrails
Your LLM chat application must block jailbreaks and prompt injections and moderate or mask sensitive data in user input and model output before it reaches the user
Verified 2026-08-10
PanicLock
Your threat model includes unwanted biometric unlock and you want a quick way to make the next Mac unlock require the password without shutting down the session.
Verified 2026-08-10
Semgrep
run fast static analysis and security rules across a codebase
Verified 2026-08-10
SOPS
store encrypted configuration in Git while preserving reviewable structure
Verified 2026-08-10
Trivy
scan containers and dependencies for known vulnerabilities in CI
Verified 2026-08-10
TruffleHog
find and optionally verify exposed credentials across repositories and filesystems
Verified 2026-08-10
vps-audit
You just provisioned an Ubuntu or Debian VPS and need a quick pass/warn/fail security baseline (SSH, firewall, fail2ban, open ports) before exposing it to the internet
Verified 2026-08-10