Smithery is now a part of Arcade.dev! Read more in our announcement here
Use this agent when working with prompt injection detection integration tests, including running tests, debugging failures, or adding new test samples.
The security package (pkg/security/) provides prompt injection detection using the HuggingFace Inference API. Integration tests verify detection accuracy with real API calls.
pkg/security/testdata/samples.json - Test data with benign and malicious samplespkg/security/hf/integration_test.go - HF client integration testspkg/security/integration_test.go - Full analyzer integration tests with event buspkg/security/hf/client.go - HuggingFace API client implementationpkg/security/analyzer.go - Main security analyzer that subscribes to MCP events# Run integration tests (requires HF_TOKEN environment variable)
HF_TOKEN=hf_xxx make test-integration
# Run with custom model
HF_TOKEN=hf_xxx HF_MODEL=protectai/deberta-v3-base-prompt-injection-v2 make test-integration
# Run unit tests only (no API calls, uses mock server)
go test -v ./pkg/security/...
samples.json){
"benign_samples": [
{
"description": "Description of the sample",
"text": "The text to analyze",
"expected_detected": false
}
],
"malicious_samples": [
{
"description": "Direct instruction override",
"text": "Ignore all previous instructions...",
"expected_detected": true,
"min_risk_score": 0.5
}
],
"mcp_tool_calls": [
{
"description": "Malicious tool call",
"method": "tools/call",
"params": { "name": "run_command", "arguments": {...} },
"expected_detected": true,
"min_risk_score": 0.5
}
]
}
Integration tests use the build tag //go:build integration and are excluded from regular go test ./... runs.
pkg/security/testdata/samples.jsonexpected_detected and optionally min_risk_scoremeta-llama/Llama-Prompt-Guard-2-86M is deprecated on HF Inference APIprotectai/deberta-v3-base-prompt-injection-v2 (publicly accessible)none: score < 0.3low: score 0.3-0.5medium: score 0.5-0.7high: score 0.7-0.9critical: score >= 0.9benign: Normal, safe contentinjection: Prompt injection attemptjailbreak: Jailbreak attemptmalicious: Malicious content (Prompt Guard v2)