aws-samples/mcp-skill
tests/fixtures/mcp-skill/SKILL.md
A skill that references external MCP servers for testing SEC-009 detection.
$ install --global
skillsauthnpx skillsauth add aws-samples/sample-agent-skill-eval mcp-skillInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 20, 2026, 3:20 PM1.8s1 file scanned
SKILL.md
- name:
- mcp-skill
- description:
- A skill that references external MCP servers for testing SEC-009 detection.
- allowed-tools:
- Bash Read
MCP Skill
This skill connects to external MCP servers for data processing.
Setup
Configure MCP servers in your settings:
{
"mcpServers": {
"data-processor": {
"command": "npx -y @untrusted-org/mcp-data-tool",
"args": ["--port", "3000"]
},
"analytics": {
"url": "https://analytics.example.net/sse"
}
}
}
You can also use the Python MCP config:
mcp_servers = {
"remote": "https://remote-mcp.example.net/mcp"
}
Usage
- Start the MCP server
- Connect to it
- Use the tools it provides
Related Skills
aws-samples/skill-eval
tools
VerifiedTrustedCommunity
Evaluate AI Agent Skills across safety, quality, reliability, and cost efficiency. Audit for security issues (secrets, injection, unsafe installs), test functional correctness with-skill vs without-skill, measure trigger precision, classify cost-efficiency tradeoffs, track version lifecycle, and generate unified grades. Use when evaluating a skill before installing, auditing marketplace skills, proving your skill works with automated tests, setting up CI/CD quality gates, or comparing two skill versions. NOT for: evaluating full agent systems, testing non-skill plugins, runtime performance benchmarking, or monitoring production agent behavior.
9SKILL.mdUpdated Apr 3, 2026
aws-samples/scoped-skill
testing
VerifiedTrustedCommunity
Test fixture for scoped vs full scanning
6SKILL.mdUpdated Apr 3, 2026
aws-samples/tests/fixtures/no-frontmatter
testing
VerifiedTrustedCommunity
No frontmatter here, just plain text. This is not a valid SKILL.md file.
6SKILL.mdUpdated Apr 3, 2026
aws-samples/good-skill
tools
VerifiedTrustedCommunity
A well-structured test skill that follows the agentskills.io spec. Use when testing skill evaluation tools.
6SKILL.mdUpdated Apr 3, 2026