← Browse
safe-ai-skill
solanabr ★ 5
This Claude Code plugin implements a security firewall for Solana AI development that gates transactions, deploys, and secrets through pre- and post-tool-use hooks, while verifying connected skills and MCPs. It runs 13 hooks across the request lifecycle (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, SessionEnd) to enforce supply-chain verification and security policies without requiring external API keys.
Install
> /plugin marketplace add solanabr/safe-ai-skill/tree/HEAD/plugins/safe-ai-skill
> /plugin install safe-ai-skill
Source: https://github.com/solanabr/safe-ai-skill/tree/HEAD/plugins/safe-ai-skill
What it's made of
13 hooks
- Commands
- 0
- Agents
- 0
- Skills
- 0
- MCP servers
- 0
- Hooks
- 13 · PostToolUse, PreToolUse, SessionEnd, SessionStart, UserPromptSubmit
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
safe-ai-skill- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (solanabr).