Code Review Graph — 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": "code-review-graph",
"source": {
"kind": "package",
"origin": "code-review-graph"
},
"server": {
"name": "code-review-graph"
}
},
"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 (30 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 (code_review_graph/changes.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`code_review_graph/changes.py:51`): 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": "code_review_graph/changes.py"
},
"evidence": "try: result = subprocess.run( [\"git\", \"diff\", \"--unified=0\", base, \"--\"], capture_outp",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "code_review_graph/changes.py",
"line": 51,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (code_review_graph/daemon.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`code_review_graph/daemon.py:1002`): 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": "code_review_graph/daemon.py"
},
"evidence": "try: proc = subprocess.Popen( cmd, cwd=repo.path, stdout=log",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "code_review_graph/daemon.py",
"line": 1002,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (code_review_graph/daemon_cli.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`code_review_graph/daemon_cli.py:175`): 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": "code_review_graph/daemon_cli.py"
},
"evidence": "try: subprocess.run([\"tail\", \"-f\", str(log_file)], check=False) except KeyboardInterrupt:",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "code_review_graph/daemon_cli.py",
"line": 175,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (code_review_graph/eval/runner.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`code_review_graph/eval/runner.py:97`): 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": "code_review_graph/eval/runner.py"
},
"evidence": "xists(): proc = subprocess.run( [\"git\", \"fetch\", \"--all\", \"--tags\"], cwd=str(repo_path),",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "code_review_graph/eval/runner.py",
"line": 97,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (code_review_graph/incremental.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`code_review_graph/incremental.py:475`): 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": "code_review_graph/incremental.py"
},
"evidence": "try: result = subprocess.run( [\"git\", \"rev-parse\", \"--abbrev-ref\", \"HEAD\"], capture_ou",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "code_review_graph/incremental.py",
"line": 475,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (code_review_graph/parser.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`code_review_graph/parser.py:365`): 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": "code_review_graph/parser.py"
},
"evidence": "ry: completed = subprocess.run( [sys.executable, \"-I\", \"-c\", code, grammar], stdin=subpr",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "code_review_graph/parser.py",
"line": 365,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (code_review_graph/skills.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`code_review_graph/skills.py:848`): 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": "code_review_graph/skills.py"
},
"evidence": "try: result = subprocess.run( [\"git\", \"rev-parse\", \"--git-path\", \"hooks\"], capture_out",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "code_review_graph/skills.py",
"line": 848,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (code_review_graph/tools/_common.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`code_review_graph/tools/_common.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": "code_review_graph/tools/_common.py"
},
"evidence": "try: result = subprocess.run( [\"git\", \"rev-parse\", \"--verify\", \"HEAD\"], capture_output",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "code_review_graph/tools/_common.py",
"line": 38,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (code_review_graph/eval/benchmarks/impact_accuracy.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`code_review_graph/eval/benchmarks/impact_accuracy.py:35`): 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": "code_review_graph/eval/benchmarks/impact_accuracy.py"
},
"evidence": "commit.\"\"\" result = subprocess.run( [\"git\", \"diff\", \"--name-only\", f\"{sha}~1\", sha], cwd=str(repo_pa",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "code_review_graph/eval/benchmarks/impact_accuracy.py",
"line": 35,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (code_review_graph/eval/benchmarks/token_efficiency.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`code_review_graph/eval/benchmarks/token_efficiency.py:28`): 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": "code_review_graph/eval/benchmarks/token_efficiency.py"
},
"evidence": "commit.\"\"\" result = subprocess.run( [\"git\", \"diff\", \"--name-only\", f\"{sha}~1\", sha], cwd=str(repo_pa",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "code_review_graph/eval/benchmarks/token_efficiency.py",
"line": 28,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"code-review-graph\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "code-review-graph"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "build_or_update_graph_tool",
"tags": [],
"reasons": {}
},
{
"tool": "run_postprocess_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_minimal_context_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_impact_radius_tool",
"tags": [],
"reasons": {}
},
{
"tool": "query_graph_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_review_context_tool",
"tags": [],
"reasons": {}
},
{
"tool": "semantic_search_nodes_tool",
"tags": [],
"reasons": {}
},
{
"tool": "embed_graph_tool",
"tags": [],
"reasons": {}
},
{
"tool": "list_graph_stats_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_docs_section_tool",
"tags": [],
"reasons": {}
},
{
"tool": "find_large_functions_tool",
"tags": [],
"reasons": {}
},
{
"tool": "list_flows_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_flow_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_affected_flows_tool",
"tags": [],
"reasons": {}
},
{
"tool": "list_communities_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_community_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_architecture_overview_tool",
"tags": [],
"reasons": {}
},
{
"tool": "detect_changes_tool",
"tags": [],
"reasons": {}
},
{
"tool": "refactor_tool",
"tags": [],
"reasons": {}
},
{
"tool": "apply_refactor_tool",
"tags": [],
"reasons": {}
},
{
"tool": "generate_wiki_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_wiki_page_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_hub_nodes_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_bridge_nodes_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_knowledge_gaps_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_surprising_connections_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_suggested_questions_tool",
"tags": [],
"reasons": {}
},
{
"tool": "traverse_graph_tool",
"tags": [],
"reasons": {}
},
{
"tool": "list_repos_tool",
"tags": [],
"reasons": {}
},
{
"tool": "cross_repo_search_tool",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "536964ffe33a607483dac139b33c12590b2cdda9a061fb185133019094f1e3da",
"stats": {
"tools": 30,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 8,
"medium": 0,
"low": 2,
"info": 1
}
}
}