vigil
robinoppenstam 作
Git & GitHub概要
AI agent safety guardrails for tool calls.
説明
このスキルでできること
Vigil validates AI agent tool calls before they execute, blocking operations like destructive shell commands, SSRF, SQL injection, path traversal, and credential leaks. It runs as a drop-in npm package with 22 rules, zero runtime dependencies, and under 2ms latency per check.
Zero runtime dependencies and sub-2ms latency mean it can run inline on every tool call without adding measurable overhead to the agent pipeline.
使いどころ
- Blocking rm -rf commands issued by autonomous agents
- Preventing SSRF in agent-driven API and HTTP calls
- Catching SQL injection before a database tool executes
- Auditing all tool calls made by a shell-executing agent
- Adding a safety layer to an existing MCP server
ワークフロー例
User asks: validate a shell command before my agent runs it
- 1
Import checkAction from vigil-agent-safety
- 2
Pass the tool name and params object to checkAction
- 3
Receive a decision (ALLOW, BLOCK, or ESCALATE) with a reason string
- 4
Block execution or proceed based on the returned decision
BLOCK: Destructive command pattern — the rm -rf / call is rejected before execution
要件
- vigil-agent-safety npm package
インストール
clawhub install robinoppenstam/vigilCLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。