using-mcp
Discover, connect to, and invoke tools on referenced MCP servers. Load this skill when an MCP server is referenced through an mcp:// typed link or MCP mention.
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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 workflow connects to and invokes tools on Model Context Protocol (MCP) servers, which can return arbitrary outsider-authored content during tool calls and server inspection.
- Repository
dtyq/magic
- Revision
0f1432c
- 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.