Patronus Security CLI — Security skill for Claude Code
Security scanner and runtime protection for AI coding agents.
How to install Patronus Security CLI
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open patronus-protect/patronus-security-cli and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Patronus Security CLI does
Security scanner and runtime protection for AI coding agents. Detects prompt injection, secrets, PII, and unsafe tool activity across Codex, Claude Code, and DeepSeek Harness.
Alternatives in Security
- Security Guidance — Hook that warns about command injection, XSS, and unsafe patterns 14k ★
- Security Guardian — Comprehensive security analysis for RTK CLI tool, focusing on command injection, shell escaping, hook security 11.9k ★
- Promptmap — Security scanner for custom LLM apps 1.2k ★
README
Patronus Security
Local-first runtime protection and security scans for AI agents.
Patronus Security combines the Patronus Security CLI (the `patronus-security-scanner` executable) with optional Runtime Protection integrations for Codex, Claude Code and DeepSeek Harness. Patronus Ark powers detection. The integrations inspect external text before it reaches the model; completed findings keep dangerous content behind a verifiable receipt.
Plugins
![]() Codex |
Claude Code |
DeepSeek Harness |
| Native prompt, tool-result and MCP-result hooks. | Native lifecycle, prompt and result hooks. | Native Cordis request and response gates. |
Choose the hosts you use during onboarding. Each plugin page explains its hooks, protected flow and degraded behavior.
Patronus Security is an independent project and is not endorsed by OpenAI, Anthropic or DeepSeek. Third-party names and logos identify compatibility only; see [Third-party notices](THIRD_PARTY_NOTICES.md).
Install
Install the latest release on macOS or Linux:
curl -fsSL https://github.com/patronus-protect/patronus-security-cli/releases/latest/download/install.sh | sh
The installer detects the platform, verifies the matching CLI artifact, installs `pat
Related Skills
Kiteguard
Open-source runtime security guardrails for Claude Code, Cursor, and Gemini CLI — blocks dangerous commands, d
Arcjet Py
Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data r
Claude Code Security
Progressive hardening framework covering agent config protection, hooks, runtime security, injection preventio
Skillguard
Security scanner for AI agent skills. Detects prompt injection, data exfiltration, and malicious payloads befo
Code Validator
Static security scanner purpose-built for AI-generated code (Claude Code, GitHub Copilot, ChatGPT, Cursor). De
Security Sweep
Comprehensive security scanner covering OWASP Top 10 (2025), Mobile Top 10 (2024), and LLM Top 10 (2025). Scan
Related Agents
Tp Audit Scanner
Use this when the user asks for a security / quality audit, pre-release sweep, or "scan this for issues". Find
Sec Auditor
Real-time PII protection and SQL/NoSQL injection blocking during data processing. Invoke when working with use
Gitnexus Security Boundary Reviewer
GitNexus security and trust-boundary reviewer. Use for auth, permissions, secrets, injection, unsafe parsing,
