Autodev X — the complete, unedited output of the deterministic mcptrustchecker engine v1.8.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.8.0",
"methodologyVersion": "mcptrustchecker-1.8"
},
"target": {
"id": "autodev-x",
"source": {
"kind": "package",
"origin": "autodev-x"
},
"server": {
"name": "autodev-x"
}
},
"grade": "C",
"score": {
"score": 71,
"threatScore": 78,
"grade": "C",
"band": "C",
"gateCap": "C",
"categorySubtotals": {
"injection": 0,
"exfiltration": 22,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-008",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"rawWeight": 22,
"confidenceMult": 1,
"diminishingFactor": 1,
"appliedPenalty": 22
},
{
"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": [
"1 confirmed high finding → grade capped at C"
],
"methodologyVersion": "mcptrustchecker-1.8"
},
"capability": {
"level": "high",
"reasons": [
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"sensitive-source",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (9 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-006",
"title": "Reads a sensitive credential path or dumps the environment (src/autodev/mcp_server/path_safety.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/autodev/mcp_server/path_safety.py:31`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. 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": "src/autodev/mcp_server/path_safety.py"
},
"evidence": "/ *.pem globs) \"id_rsa\", \"id_dsa\", \"id_ecdsa\", \"id_ed25519\", \"id_xmss\",",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "src/autodev/mcp_server/path_safety.py",
"line": 31,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-008",
"title": "Hardcoded GitHub token in server code (tests/unit/test_secret_redaction.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"description": "A live-looking GitHub token is hardcoded in `tests/unit/test_secret_redaction.py:80`. Secrets in source ship to everyone who installs the package and are a direct credential leak.",
"remediation": "Remove the secret, rotate it, and load credentials from the environment or a secret store.",
"location": {
"kind": "server",
"name": "tests/unit/test_secret_redaction.py"
},
"evidence": "GitHub token: ghp_…(redacted)",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"secretType": "github-token",
"file": "tests/unit/test_secret_redaction.py",
"line": 80
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/autodev/adapters/a2a/transports/local_shell.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/autodev/adapters/a2a/transports/local_shell.py:70`): 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": "src/autodev/adapters/a2a/transports/local_shell.py"
},
"evidence": "try: proc = subprocess.run( argv, env=os.environ.copy(), cap",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/autodev/adapters/a2a/transports/local_shell.py",
"line": 70,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/autodev/adapters/mcp_client.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/autodev/adapters/mcp_client.py:118`): 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": "src/autodev/adapters/mcp_client.py"
},
"evidence": "self._proc = subprocess.Popen( argv, stdin=subprocess.PIPE, s",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/autodev/adapters/mcp_client.py",
"line": 118,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/autodev/adapters/opus_adapter.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/autodev/adapters/opus_adapter.py:84`): 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": "src/autodev/adapters/opus_adapter.py"
},
"evidence": "try: proc = subprocess.run( argv, env=os.environ.copy(), cap",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/autodev/adapters/opus_adapter.py",
"line": 84,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/autodev/agents/adversarial_reviewer.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/autodev/agents/adversarial_reviewer.py:38`): 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": "src/autodev/agents/adversarial_reviewer.py"
},
"evidence": "KER), (\"subprocess.*shell=True\", True, \"injection\", \"subprocess shell=True — command injection\", Severity.BLOCK",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/autodev/agents/adversarial_reviewer.py",
"line": 38,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/autodev/agents/document_project.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/autodev/agents/document_project.py:23`): 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": "src/autodev/agents/document_project.py"
},
"evidence": "try: result = subprocess.run( [\"git\", *args], cwd=cwd, capture_output=True",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/autodev/agents/document_project.py",
"line": 23,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/autodev/agents/investigator.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/autodev/agents/investigator.py:234`): 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": "src/autodev/agents/investigator.py"
},
"evidence": "y: result = subprocess.run( [\"gh\", \"issue\", \"view\", ticket_id, \"--json\", \"title,body,state,l",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/autodev/agents/investigator.py",
"line": 234,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/autodev/context_providers/search_provider.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/autodev/context_providers/search_provider.py:40`): 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": "src/autodev/context_providers/search_provider.py"
},
"evidence": "try: result = subprocess.run( [\"rg\", \"--no-heading\", \"--line-number\", \"-i\", \"-m\", \"1\",",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/autodev/context_providers/search_provider.py",
"line": 40,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/autodev/coverage_gate.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/autodev/coverage_gate.py:26`): 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": "src/autodev/coverage_gate.py"
},
"evidence": "exec\") try: exec(code, ns) except SystemExit: raise if __name__ == \"__main__\": main()",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/autodev/coverage_gate.py",
"line": 26,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/autodev/executors/_fs_observer.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/autodev/executors/_fs_observer.py:24`): 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": "src/autodev/executors/_fs_observer.py"
},
"evidence": "l: try: r = subprocess.run( [\"git\", \"rev-parse\", \"--is-inside-work-tree\"], cwd=path,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/autodev/executors/_fs_observer.py",
"line": 24,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/autodev/executors/claude_code_executor.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/autodev/executors/claude_code_executor.py:161`): 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": "src/autodev/executors/claude_code_executor.py"
},
"evidence": "rue) proc = subprocess.run( argv, cwd=request.repo_path, env",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/autodev/executors/claude_code_executor.py",
"line": 161,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/integration/test_parallel_review_5sections.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/integration/test_parallel_review_5sections.py:49`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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": "tests/integration/test_parallel_review_5sections.py"
},
"evidence": "jection\\n\" \" requests.get('http://example.com', timeout=None) # network flake\\n\" \" now = datetime",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "tests/integration/test_parallel_review_5sections.py",
"line": 49,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment in packaging/dev tooling (tests/integration/test_mcp_path_secret_denial.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/integration/test_mcp_path_secret_denial.py:88`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. 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": "tests/integration/test_mcp_path_secret_denial.py"
},
"evidence": "e_path(\"/home/user/.ssh/id_rsa.key\") def test_rejects_secret_substring_in_basename(self): \"\"\"my-secret-file",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "tests/integration/test_mcp_path_secret_denial.py",
"line": 88,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in packaging/dev tooling (tests/unit/test_adversarial_reviewer.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/unit/test_adversarial_reviewer.py:104`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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": "tests/unit/test_adversarial_reviewer.py"
},
"evidence": "d injection finding for eval()\" assert injection[0].severity_finding is not None # -------------------------------",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/unit/test_adversarial_reviewer.py",
"line": 104,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "autodev_scan",
"tags": [],
"reasons": {}
},
{
"tool": "autodev_classify_input",
"tags": [],
"reasons": {}
},
{
"tool": "autodev_create_prd",
"tags": [],
"reasons": {}
},
{
"tool": "autodev_deliver_project",
"tags": [],
"reasons": {}
},
{
"tool": "autodev_run_issue",
"tags": [],
"reasons": {}
},
{
"tool": "autodev_report",
"tags": [],
"reasons": {}
},
{
"tool": "autodev_roundtable",
"tags": [],
"reasons": {}
},
{
"tool": "autodev_release_check",
"tags": [],
"reasons": {}
},
{
"tool": "autodev_list_runs",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "fea9d75c8cf7f034e9bfc5c5601f17b23968d3cd7a16207e1cc1aabe88616118",
"stats": {
"tools": 9,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 12,
"medium": 0,
"low": 3,
"info": 0
}
}
}