Codegraph Nav — 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": "codegraph-nav",
"source": {
"kind": "package",
"origin": "codegraph-nav"
},
"server": {
"name": "codegraph-nav"
}
},
"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": [
"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 (20 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/codegraph_nav/code_navigator.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/codegraph_nav/code_navigator.py:149`): 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/codegraph_nav/code_navigator.py"
},
"evidence": "p12\", \"*.pfx\", \"id_rsa*\", \"id_ed25519*\", \"id_ecdsa*\", \"*.crt\", \"*.cer\", # Config files with",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "src/codegraph_nav/code_navigator.py",
"line": 149,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/codegraph_nav/code_navigator.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/codegraph_nav/code_navigator.py:822`): 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/codegraph_nav/code_navigator.py"
},
"evidence": "y: result = subprocess.run( [\"git\", \"rev-parse\", \"--git-dir\"], cwd=self.root",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/codegraph_nav/code_navigator.py",
"line": 822,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/codegraph_nav/code_search.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/codegraph_nav/code_search.py:593`): 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/codegraph_nav/code_search.py"
},
"evidence": "y: result = subprocess.run( [\"git\", \"diff\", \"--name-only\", commit, \"HEAD\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/codegraph_nav/code_search.py",
"line": 593,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/codegraph_nav/graph/query.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/codegraph_nav/graph/query.py:165`): 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/codegraph_nav/graph/query.py"
},
"evidence": "try: result = subprocess.run( [\"git\", \"diff\", \"--unified=0\", base, \"--\"], cwd=root_pat",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/codegraph_nav/graph/query.py",
"line": 165,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/codegraph_nav/mcp/server.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/codegraph_nav/mcp/server.py:1606`): 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/codegraph_nav/mcp/server.py"
},
"evidence": "result = subprocess.run( [\"git\", \"diff\", \"--name-only\", base, \"HEAD\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/codegraph_nav/mcp/server.py",
"line": 1606,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "codegraph_scan",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_search",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_read",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_stats",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_get_hubs",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_get_context",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_get_dependencies",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_get_structure",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_get_minimal_context",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_test_gaps",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_graph_build",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_blast_radius",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_list_flows",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_detect_changes",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_search_graph",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_list_communities",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_get_community",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_get_architecture_overview",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_list_routes",
"tags": [],
"reasons": {}
},
{
"tool": "codegraph_list_schemas",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "f8efb6dcbc752e4d33938b9e13b8dbf74a614b0b89a0a4622d481e1dd978bb5b",
"stats": {
"tools": 20,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 5,
"medium": 0,
"low": 0,
"info": 0
}
}
}