Kiteguard — Security skill for Claude Code
Open-source runtime security guardrails for Claude Code, Cursor, and Gemini CLI — blocks dangerous commands, detects prompt injection, and prevents PII leakage before it happens.
How to install Kiteguard
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open DhivakaranRavi/kiteguard and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Kiteguard does
Open-source runtime security guardrails for Claude Code, Cursor, and Gemini CLI — blocks dangerous commands, detects prompt injection, and prevents PII leakage before it happens.
Alternatives in Security
- Free Code — The free build of Claude Code 8.1k ★
- Anthropic Cybersecurity Skills — 734+ structured cybersecurity skills for AI agents · MITRE ATT&CK mapped · agentskills.io open standard · Work 3.8k ★
- ThinkWatch — Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII 817 ★
README
Open-source runtime security guardrails for Claude Code, Cursor, and Gemini CLI
kiteguard watches every move your AI agent makes — and stops the dangerous ones.
[](https://github.com/DhivakaranRavi/kiteguard/actions/workflows/ci.yml) [](LICENSE)   
Install
**Option 1 — Install script (quickest):**
curl -sSL https://raw.githubusercontent.com/DhivakaranRavi/kiteguard/main/scripts/install.sh | bash
**Option 2 — Build from source (recommended for security-conscious users):**
git clone https://github.com/DhivakaranRavi/kiteguard.git
cd kiteguard
cargo build --release
sudo install -m755 target/release/kiteguard /usr/local/bin/kiteguard
# Register with your agent(s):
kiteguard init --claude-code # Claude Code
kiteguard init --cursor # Cursor
kiteguard init --gemini # Gemini CLI
No dependencies beyond a Rust toolchain. Get Rust at [rustup.rs](https://rustup.rs).
Why kiteguard
AI coding agents — Claude Code, Cursor, and Gemini CLI — autonomously execute shell commands, read your entire codebase, fetch external URLs, and modify files without asking for confirmation. That power also means:
- A poisoned README can instruct
Related Skills
Patronus Security CLI
Security scanner and runtime protection for AI coding agents. Detects prompt injection, secrets, PII, and unsa
AegisGate
Open-source security gateway for LLM APIs — prompt injection detection, PII redaction, dangerous response sani
Agent Security Hooks
Security hooks for AI coding assistants (Claude Code, Cursor, Gemini CLI) - block dangerous commands, protect
Agent Observability Logging
Log everything that happens inside your agent system, from deterministic code: hook-written audit events, inva
Intutic
The open source circuit breaker for AI agents. Real-time security, secret DLP, graph guardrails and loop burn
HarnessDesk
Open-source control plane for coding agents you own — run Codex, Claude Code, Gemini, Cursor and ACP agents si
Related Agents
Security Privacy Guardian
Use when validating PII handling (LGPD/GDPR), secret leakage in code/prompts/traces, eval-case sanitization, o
Runtime Reviewer
Reviews a diff for what happens when it runs — empty and null data, error paths, leaks, races, re-renders, two
Project Automation Auditor
Audits a project's automation and verification posture: test runner, formatter/linter PostToolUse hooks, PreTo