Rules or configurationSecurity and privacy
safe-solana-builder
An AI coding skill for security-focused Solana programs, test scaffolds, and checklists.
An AI coding skill for security-focused Solana programs, test scaffolds, and checklists.
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.
Resource types
Use cases
Capabilities
Audit AI-generated applications for common security mistakes before release.
Lets Claude Code run ffuf for authorized discovery of paths, files, subdomains, and API endpoints.
Audience
Public GitHub facts last synced Jul 14, 2026.
Run supported always-on AI agents inside managed NVIDIA OpenShell sandboxes.
Plan and run authorized penetration tests with autonomous agents in an isolated environment.