References external URL — review for indirect prompt injection risk
Vettd coreOWASP LLM03External URL(s) detected in SKILL.md — referenced content can change after audit
Public SkillWarnings
mcp-builder
anthropics
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Security Summary
This skill includes a SKILL.md descriptor and ships with scripts. Security observation: references external URL.
Source
GitHub
Last Scanned
May 1, 2026
License
Complete terms in LICENSE.txt
Category
security
No prompt injection or jailbreak signals detected
Vettd coreScanned text content for instruction override, jailbreak framing, credential solicitation, and embedded injection markers
No secrets or unsafe code patterns detected
Vettd coreScanned all files for credentials, private keys, and code-level risks (eval, shell exec, destructive ops)
Category
best practices
Examples included
Vettd coreFound code blocks, input/output samples, or an examples section — concrete samples help agents pattern-match effectively
Progressive disclosure used
Vettd coreSKILL.md body references files in references/, scripts/, or assets/ — agents can load additional context on demand instead of consuming everything upfront
SKILL.md body length is reasonable
Vettd core231 lines (recommended: under 500)
Step-by-step workflow found
Vettd coreStructured procedures improve reliability for complex tasks
Category
description
Description includes usage context
Vettd coreGood: description explains when to activate the skill
Description within character limit
Vettd core277/1024 characters used
Category
evals
No evaluation test cases
Vettd coreAdd an evals/ directory with test prompts and expected outputs to measure skill quality
Category
scripts
scripts/connections.py: No --help support
Vettd coreAdd argument parsing with --help output so agents know the script's interface
scripts/evaluation.py: CLI help supported
Vettd coreScript documents its interface via --help or argument parsing
scripts/evaluation.py: Structured output format
Vettd coreUses JSON/CSV output which is easily parseable by agents
Category
structure
scripts/ directory present
Vettd coreBundled executable scripts found
SKILL.md present
Vettd coreRequired skill definition file found
Valid name field
Vettd coreName "mcp-builder" follows spec (lowercase, hyphens, ≤64 chars)