Bicameral — the complete, unedited output of the deterministic mcptrustchecker engine v1.5.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.5.0",
"methodologyVersion": "mcptrustchecker-1.4"
},
"target": {
"id": "bicameral-mcp",
"source": {
"kind": "package",
"origin": "bicameral-mcp"
},
"server": {
"name": "bicameral-mcp"
}
},
"grade": "F",
"score": {
"score": 40,
"threatScore": 51,
"grade": "F",
"band": "F",
"gateCap": "D",
"categorySubtotals": {
"injection": 0,
"exfiltration": 40.7,
"permissions": 6.3,
"supply-chain": 2.1,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"kind": "threat",
"ruleId": "MTC-SRC-008",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"rawWeight": 22,
"confidenceMult": 1,
"diminishingFactor": 1,
"appliedPenalty": 22
},
{
"kind": "threat",
"ruleId": "MTC-SRC-008",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"rawWeight": 22,
"confidenceMult": 1,
"diminishingFactor": 0.5,
"appliedPenalty": 11
},
{
"kind": "threat",
"ruleId": "MTC-SRC-008",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"rawWeight": 22,
"confidenceMult": 1,
"diminishingFactor": 0.25,
"appliedPenalty": 5.5
},
{
"kind": "threat",
"ruleId": "MTC-SRC-008",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"rawWeight": 22,
"confidenceMult": 1,
"diminishingFactor": 0.1,
"appliedPenalty": 2.2
},
{
"kind": "threat",
"ruleId": "MTC-SUP-011",
"category": "supply-chain",
"severity": "low",
"confidence": "strong",
"rawWeight": 3,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 2.1
},
{
"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": "none",
"label": "publisher verification (none) — trust in the source of the package",
"appliedPenalty": 5
},
{
"kind": "client",
"term": "coverage-honesty",
"level": "source",
"label": "inspection depth (source) — how much of the target the scan could see",
"appliedPenalty": 0
}
],
"gatesFired": [
"4 confirmed high findings → grade capped at D"
],
"methodologyVersion": "mcptrustchecker-1.5"
},
"capability": {
"level": "high",
"reasons": [
"can execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": false,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command \"npx -y <package>\"."
]
},
"findings": [
{
"ruleId": "MTC-SRC-008",
"title": "Hardcoded AWS access key id in server code (handlers/sensitive_patterns.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"description": "A live-looking AWS access key id is hardcoded in `handlers/sensitive_patterns.py:145`. 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": "handlers/sensitive_patterns.py"
},
"evidence": "AWS access key id: AKIA…(redacted)",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"secretType": "aws-access-key",
"file": "handlers/sensitive_patterns.py",
"line": 145
}
},
{
"ruleId": "MTC-SRC-008",
"title": "Hardcoded AWS access key id in server code (tests/test_ingest_sensitive_catalog.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"description": "A live-looking AWS access key id is hardcoded in `tests/test_ingest_sensitive_catalog.py:36`. 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/test_ingest_sensitive_catalog.py"
},
"evidence": "AWS access key id: AKIA…(redacted)",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"secretType": "aws-access-key",
"file": "tests/test_ingest_sensitive_catalog.py",
"line": 36
}
},
{
"ruleId": "MTC-SRC-008",
"title": "Hardcoded AWS access key id in server code (tests/test_ingest_sensitive_detect.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"description": "A live-looking AWS access key id is hardcoded in `tests/test_ingest_sensitive_detect.py:19`. 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/test_ingest_sensitive_detect.py"
},
"evidence": "AWS access key id: AKIA…(redacted)",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"secretType": "aws-access-key",
"file": "tests/test_ingest_sensitive_detect.py",
"line": 19
}
},
{
"ruleId": "MTC-SRC-008",
"title": "Hardcoded AWS access key id in server code (tests/test_ingest_sensitive_gate.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"description": "A live-looking AWS access key id is hardcoded in `tests/test_ingest_sensitive_gate.py:38`. 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/test_ingest_sensitive_gate.py"
},
"evidence": "AWS access key id: AKIA…(redacted)",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"secretType": "aws-access-key",
"file": "tests/test_ingest_sensitive_gate.py",
"line": 38
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (tests/eval/_preflight_m6_seeder.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tests/eval/_preflight_m6_seeder.py:1`): 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/eval/_preflight_m6_seeder.py"
},
"evidence": "eval (",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/eval/_preflight_m6_seeder.py",
"line": 1
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (tests/eval_decision_relevance.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tests/eval_decision_relevance.py:264`): 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/eval_decision_relevance.py"
},
"evidence": "eval (",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/eval_decision_relevance.py",
"line": 264
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (tests/eval_preflight_skill_summary.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tests/eval_preflight_skill_summary.py:207`): 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/eval_preflight_skill_summary.py"
},
"evidence": "eval (",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/eval_preflight_skill_summary.py",
"line": 207
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (tests/test_preflight_m6_eval.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tests/test_preflight_m6_eval.py:1`): 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/test_preflight_m6_eval.py"
},
"evidence": "eval (",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/test_preflight_m6_eval.py",
"line": 1
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (code_locator_runtime.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`code_locator_runtime.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": "code_locator_runtime.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "code_locator_runtime.py",
"line": 70
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (events/writer.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`events/writer.py:85`): 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": "events/writer.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "events/writer.py",
"line": 85
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (handlers/ingest.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`handlers/ingest.py:508`): 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": "handlers/ingest.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "handlers/ingest.py",
"line": 508
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (handlers/link_commit.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`handlers/link_commit.py:50`): 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": "handlers/link_commit.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "handlers/link_commit.py",
"line": 50
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (handlers/update.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`handlers/update.py:296`): 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": "handlers/update.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "handlers/update.py",
"line": 296
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (ledger/adapter.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`ledger/adapter.py:800`): 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": "ledger/adapter.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "ledger/adapter.py",
"line": 800
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (ledger/status.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`ledger/status.py:45`): 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": "ledger/status.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "ledger/status.py",
"line": 45
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (ledger_locator/_project_id.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`ledger_locator/_project_id.py:30`): 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": "ledger_locator/_project_id.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "ledger_locator/_project_id.py",
"line": 30
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (release/evidence_collect.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`release/evidence_collect.py:49`): 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": "release/evidence_collect.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "release/evidence_collect.py",
"line": 49
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (release/sbom_emit.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`release/sbom_emit.py:64`): 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": "release/sbom_emit.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "release/sbom_emit.py",
"line": 64
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (tests/test_skill_governance_lint.py)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`tests/test_skill_governance_lint.py:199`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). 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/test_skill_governance_lint.py"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "tests/test_skill_governance_lint.py",
"line": 199
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package has no source repository",
"category": "supply-chain",
"severity": "low",
"confidence": "strong",
"description": "\"bicameral-mcp\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
"remediation": "Prefer packages that link to public, reviewable source.",
"location": {
"kind": "package",
"name": "bicameral-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [],
"surfaceDigest": "3d778df155a832a2f40c87cbace377b70e7245de495b0c231db0c1ffe850d4f1",
"stats": {
"tools": 0,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 18,
"medium": 1,
"low": 1,
"info": 0
}
}
}