safe-ai-skill

safe-ai-skill is a plugin for Claude Code from solanabr/safe-ai-skill. Its token cost is not measured, scanned A, original, MIT.

A security and supply-chain checking add-on for Solana AI development, covering transactions, deployments, secrets, skills, and MCPs.

In plain words
What is it for?
It gates Solana-related transactions, deployments, and secret handling, and verifies skills and MCPs used by the development setup.
Why use it?
It adds checks before sensitive development actions and before using external add-ons or tool connections.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add solanabr/safe-ai-skill
agentmods
npx agentmods add plugins/solanabr/safe-ai-skill/safe-ai-skill
Clone the repo
git clone --depth 1 https://github.com/solanabr/safe-ai-skill

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for safe-ai-skill

README.md
[![agentmods](https://agentmods.dev/badge/plugins/solanabr/safe-ai-skill/safe-ai-skill.svg)](https://agentmods.dev/plugins/solanabr/safe-ai-skill/safe-ai-skill)
Your own site
<a href="https://agentmods.dev/plugins/solanabr/safe-ai-skill/safe-ai-skill"><img src="https://agentmods.dev/badge/plugins/solanabr/safe-ai-skill/safe-ai-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

safe-ai-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/safe-ai-skill/.claude-plugin/plugin.json · 20 lines

What it actually says

{
  "name": "safe-ai-skill",
  "version": "1.0.0",
  "description": "Security firewall + supply-chain verifier for Solana AI dev — gates transactions/deploys/secrets and verifies skills/MCPs.",
  "author": {
    "name": "Superteam Brazil"
  },
  "license": "MIT",
  "keywords": [
    "solana",
    "security",
    "firewall",
    "supply-chain",
    "ai",
    "claude-code",
    "mcp"
  ],
  "hooks": "./hooks/hooks.json"
}
Contents

What it installs

The manifest is a name and a version. 4 hooks travel with it, and installing the plugin installs all of them. Each is measured on its own page, and each can be installed alone.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 20 lines scan A 909d48ee7480

Subscribe to this mod's changes

safe-ai-skill is a plugin published in the GitHub repository solanabr/safe-ai-skill (5 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.