Valvur — Security skill for Claude Code
Offline security scanning for AI-generated code: seven open-source scanners and AI-specific checks in one command.
How to install Valvur
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open MaverickHQ/valvur and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Valvur does
Offline security scanning for AI-generated code: seven open-source scanners and AI-specific checks in one command. It finds secrets, vulnerable, hallucinated and malicious dependencies, poisoned agent configuration, and infrastructure and code flaws. An MCP server for Claude Code and Kiro, and a CLI. Your source never leaves your machine.
Alternatives in Security
- Google Workspace Model Armor — Filter user-generated content for safety 21.6k ★
- Security Scan Report — Generated: 2026-04-10 20:48 UTC Skills scanned: 134 Total findings: 836 Critical: 32 High: 50 Safe skills: 100 18.1k ★
- Security Best Practices — Review code for language-specific security vulnerabilities 14.6k ★
README
**Offline security scanning for AI-generated code.**
Seven open-source scanners and AI-specific checks, in one command and one ranked report.
[](https://pypi.org/project/valvur/) [](https://pypi.org/project/valvur/) [](https://github.com/MaverickHQ/valvur/actions/workflows/ci.yml) [](https://scorecard.dev/viewer/?uri=github.com/MaverickHQ/valvur) [](LICENSE)
Scorecard's Code-Review, Branch-Protection and Contributors checks need a second maintainer; valvur has one ([MAINTAINERS.md](MAINTAINERS.md)).
**Status: `1.5.1`**, the version this tree declares; the PyPI badge above shows what `pip install valvur` serves, and [the CHANGELOG](CHANGELOG.md) what each version changed.
**In Claude Code:** `/plugin marketplace add MaverickHQ/valvur`, then `/plugin install valvur@valvur`, and ask it to scan the project.
**From a terminal,** with Docker or Podman running: `uvx valvur scan`.

Why valvur
- Seven scanners, one report. Gitleaks, Trivy, OSV-Scanner, Opengrep, Checkov, zizmor and Syft, pinned, installed and run for you in one container, beside valvur's own checks for AI-written code. A vulnerability two of them report is one finding, not two, and everything is ranked together.
- Nothing leaves your machine, provably. No account, no API key, no telemetry. The Scanne
Related Skills
Lunacy Studio Skills
A seven-skill security toolkit for Claude Code that audits any web project, finds the holes, and closes them —
Dep Crusade
Unleash parallel Dependency Purist agents to audit every package.json, lockfile, and import for outdated, vuln
Patchbot
Vulnerability scanning with your own scanners and threat feeds, plus a coding agent that opens the fix PR. CLI
Clawguard
Clawguard is a security scanning and interception tool for OpenClaw, offering comprehensive diagnostics for sk
Cloud Config Audit
Assess infrastructure-as-code security with offline scanning and evidence-based finding review.
MCP Skills Vault
Offline security check for MCP server configs (.mcp.json, VS Code, Cursor, Claude Code) — GitHub Action, pre-c
Related Agents
Supply Chain Framework Auditor
Audits dependency CVEs, malicious or over-permissioned SDKs, build-pipeline leftovers (debug flags, test endpo
Seraph
Static security audit of a repo's code and config (exposed secrets, missing authorisation, injection surfaces,
License Compliance Guardian
License compliance scanning, legal risk assessment, and open source governance.