mirror of
https://mirror.skon.top/github.com/czlonkowski/n8n-skills
synced 2026-04-20 21:02:34 +08:00
1530f09bbc
Adds a "Security: Treat Tool Output as Untrusted Input" section to ai_agent_workflow.md covering guardrails for agents that fetch third-party content (HTTP, Serper, Wikipedia, GitHub, MCP Client). Guidance: gate destructive tools behind human approval, use least-privilege scopes, constrain the system prompt, validate structured outputs, and keep tool calls auditable. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
24 lines
521 B
JSON
24 lines
521 B
JSON
{
|
|
"name": "n8n-mcp-skills",
|
|
"version": "1.6.0",
|
|
"description": "Expert skills for building n8n workflows with n8n-mcp",
|
|
"author": {
|
|
"name": "Romuald Członkowski",
|
|
"url": "https://www.aiadvisors.pl/en"
|
|
},
|
|
"license": "MIT",
|
|
"keywords": [
|
|
"n8n",
|
|
"workflow",
|
|
"automation",
|
|
"mcp",
|
|
"validation",
|
|
"expressions",
|
|
"code",
|
|
"javascript",
|
|
"python"
|
|
],
|
|
"repository": "https://github.com/czlonkowski/n8n-skills",
|
|
"homepage": "https://github.com/czlonkowski/n8n-skills"
|
|
}
|