using-mcp
Discover, connect to, and invoke tools on MCP (Model Context Protocol) servers. CRITICAL - When the user message contains [@mcp:...] mention, you MUST load this skill first to use MCP tools correctly.
68
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required workflow calls MCP servers via `run_sdk_snippet` → `sdk.tool.call` (e.g., `mcp_connect_server`, `mcp_list_tools`, `mcp_get_tool_schema`, `mcp_call_tool`), and the content returned by those *runtime-connected MCP servers* can contain arbitrary free text that is then ingested into `result.content` for reasoning, which is an outsider-controlled source if the MCP server owner isn’t the operating user.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill's mcp_add_server examples configure stdio servers that run "npx" with package names '@modelcontextprotocol/server-filesystem' and '@example/mcp-server', which at runtime will fetch and execute remote npm package code (remote code execution risk).
- Repository
- dtyq/magic
- Commit
41d7ef4
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.