Rules or configurationSecurity and privacy

vibe-security-skill

Audit AI-generated applications for common security mistakes before release.

Stars: 860
Forks: 107
Updated: Updated Jul 14, 2026

Rules or configurationSecurity and privacy

vibe-security-skill

Audit AI-generated applications for common security mistakes before release.

Stars: 860
Forks: 107
Updated: Updated Jul 14, 2026

Rules or configurationSecurity and privacyClaude Code

ffuf_claude_skill

@jthackPython

Lets Claude Code run ffuf for authorized discovery of paths, files, subdomains, and API endpoints.

Stars: 195
Forks: 18
License: Not declared

Rules or configurationSecurity and privacy

safe-solana-builder

@Frankcastleauditor

An AI coding skill for security-focused Solana programs, test scaffolds, and checklists.

Project overview

Safe Solana Builder is an AI coding skill for Claude or Cursor that applies a security-first workflow before Solana code is written. It selects Anchor, native Rust, or Pinocchio, assesses risk, and applies rules for account validation, PDAs, CPIs, arithmetic, Token-2022, and related failure modes. Each request can produce a full project scaffold, compilable program, test file, and security checklist; security edge-case tests are scaffolded with TODO bodies, positioning the skill as a first hardening layer before audit.

Stars: 133
Forks: 21
License: Not declared

Agent runtimeSecurity and privacyOpenClaw

NemoClaw

@NVIDIATypeScript

Run supported always-on AI agents inside managed NVIDIA OpenShell sandboxes.

Project overview

Set up OpenClaw, Hermes, or LangChain Deep Agents inside NVIDIA OpenShell with a reference stack that combines guided onboarding, routed inference, network policy, and sandbox lifecycle management behind one CLI. The project focuses on safer long-running agent operation and controlled egress. It is currently described as alpha, with community support provided on a best-effort basis.

Stars: 21,703
Forks: 2,930
License: Apache-2.0

General agentSecurity and privacy

pentagi

@vxcontrolGo

Plan and run authorized penetration tests with autonomous agents in an isolated environment.

Project overview

PentAGI lets autonomous agents plan and execute authorized penetration-testing work inside an isolated Docker environment. It includes more than twenty security tools such as nmap, Metasploit, and sqlmap, and can retain useful findings for later tasks. Cloud and local models are supported; smaller open models benefit from execution monitoring and task planning at the cost of higher token usage.

Stars: 20,544
Forks: 2,718
License: MIT

vibe-security-skill

vibe-security-skill

Project overview

Repository facts

Related projects

ffuf_claude_skill

safe-solana-builder

NemoClaw

pentagi