Ai Test Failure Analyzer — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "ai-test-failure-analyzer",
"source": {
"kind": "package",
"origin": "ai-test-failure-analyzer"
},
"server": {
"name": "ai-test-failure-analyzer"
}
},
"grade": "A",
"score": {
"score": 93,
"threatScore": 100,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "client",
"term": "capability-exposure",
"level": "high",
"label": "capability blast radius (high) — client exposure if the model is manipulated",
"appliedPenalty": 6
},
{
"kind": "client",
"term": "verification-discount",
"level": "repo",
"label": "publisher verification (public source) — no provenance, but the source is public and inspectable",
"appliedPenalty": 1
},
{
"kind": "client",
"term": "coverage-honesty",
"level": "source",
"label": "inspection depth (source) — how much of the target the scan could see",
"appliedPenalty": 0
}
],
"gatesFired": [],
"methodologyVersion": "mcptrustchecker-1.9"
},
"capability": {
"level": "high",
"reasons": [
"can execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (12 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command \"npx -y <package>\"."
]
},
"findings": [
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (analyzer/evidence/collectors/contract_diff_collector.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`analyzer/evidence/collectors/contract_diff_collector.py:32`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "analyzer/evidence/collectors/contract_diff_collector.py"
},
"evidence": "space) result = subprocess.run( [\"git\", \"diff\", \"HEAD~1\", \"--\", str(rel)], cwd=str(works",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "analyzer/evidence/collectors/contract_diff_collector.py",
"line": 32,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (analyzer/evidence/collectors/dep_diff_collector.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`analyzer/evidence/collectors/dep_diff_collector.py:69`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "analyzer/evidence/collectors/dep_diff_collector.py"
},
"evidence": "try: result = subprocess.run( [\"git\", \"show\", f\"{ref}:{file_path}\"], cwd=str(workspace",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "analyzer/evidence/collectors/dep_diff_collector.py",
"line": 69,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (analyzer/evidence/git_scan.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`analyzer/evidence/git_scan.py:3`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "analyzer/evidence/git_scan.py"
},
"evidence": "use a list[str] (never shell=True), use a whitelisted subcommand, and validate commit hashes against a strict regex. Ou",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "analyzer/evidence/git_scan.py",
"line": 3,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (analyzer/github_integration.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`analyzer/github_integration.py:88`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "analyzer/github_integration.py"
},
"evidence": "try: out = subprocess.run( [\"git\", \"remote\", \"get-url\", \"origin\"], capture_output=T",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "analyzer/github_integration.py",
"line": 88,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (analyzer/security.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`analyzer/security.py:53`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "analyzer/security.py"
},
"evidence": "s can be used inline: ``subprocess.run([\"git\", *validate_git_args(a)])``. \"\"\" if not args: raise Securit",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "analyzer/security.py",
"line": 53,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "collect_failures",
"tags": [],
"reasons": {}
},
{
"tool": "read_test_intent",
"tags": [],
"reasons": {}
},
{
"tool": "scan_git_history_tool",
"tags": [],
"reasons": {}
},
{
"tool": "scan_logs_tool",
"tags": [],
"reasons": {}
},
{
"tool": "scan_config_tool",
"tags": [],
"reasons": {}
},
{
"tool": "correlate_evidence",
"tags": [],
"reasons": {}
},
{
"tool": "form_hypotheses_tool",
"tags": [],
"reasons": {}
},
{
"tool": "render_report",
"tags": [],
"reasons": {}
},
{
"tool": "create_github_issue",
"tags": [],
"reasons": {}
},
{
"tool": "analyze",
"tags": [],
"reasons": {}
},
{
"tool": "list_questions",
"tags": [],
"reasons": {}
},
{
"tool": "server_info",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "c8e2a7601b1c0bc44974ee58a9b98b8e26fca34709c47613f7500cdaae47c9c0",
"stats": {
"tools": 12,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 5,
"medium": 0,
"low": 0,
"info": 0
}
}
}