create-mcp-integration — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited create-mcp-integration (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Follow the create-mcp-integration skill workflow to scaffold a new MCP server integration for a Claude Code plugin.
$ARGUMENTS — optional MCP server name or service description (e.g. postgres,github, slack). Omit to start with discovery.
$ARGUMENTS names a server or service, use it to seed Phase 1 discovery(stdio / SSE / streamable-http), authentication method, which tools to expose, configuration fields, then generate the .mcp.json entry and any supporting config
.mcp.json server entry with full configuration (command/url, env vars, allowed tools) and instructions for obtaining credentials and verifying the connection with /mcp.
$ARGUMENTS is empty: begin with server type selectionstreamable-http transport for new hosted integrations over SSE~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.