Oath — 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": "oath-mcp",
"source": {
"kind": "package",
"origin": "oath-mcp"
},
"server": {
"name": "oath-mcp"
}
},
"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-1.8"
},
"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 (16 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/oath/mcp/tools/enumerate_credential_artifacts.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/oath/mcp/tools/enumerate_credential_artifacts.py:69`): 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/oath/mcp/tools/enumerate_credential_artifacts.py"
},
"evidence": "id_rsa",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "src/oath/mcp/tools/enumerate_credential_artifacts.py",
"line": 69
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (tests/unit/test_enumerate_credential_artifacts.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tests/unit/test_enumerate_credential_artifacts.py:85`): 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/unit/test_enumerate_credential_artifacts.py"
},
"evidence": "id_rsa",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "tests/unit/test_enumerate_credential_artifacts.py",
"line": 85
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/oath/mcp/evidence_handle.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/oath/mcp/evidence_handle.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/oath/mcp/evidence_handle.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/oath/mcp/evidence_handle.py",
"line": 40
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"image_path\" on \"oath_mount\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"oath_mount\" takes a path parameter \"image_path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "oath_mount",
"field": "inputSchema.properties.image_path"
},
"data": {
"param": "image_path"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"evtx_path\" on \"parse_evtx\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"parse_evtx\" takes a path parameter \"evtx_path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "parse_evtx",
"field": "inputSchema.properties.evtx_path"
},
"data": {
"param": "evtx_path"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"mft_path\" on \"parse_mft\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"parse_mft\" takes a path parameter \"mft_path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "parse_mft",
"field": "inputSchema.properties.mft_path"
},
"data": {
"param": "mft_path"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"filter_path\" on \"parse_mft\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"parse_mft\" takes a path parameter \"filter_path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "parse_mft",
"field": "inputSchema.properties.filter_path"
},
"data": {
"param": "filter_path"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"amcache_path\" on \"parse_amcache\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"parse_amcache\" takes a path parameter \"amcache_path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "parse_amcache",
"field": "inputSchema.properties.amcache_path"
},
"data": {
"param": "amcache_path"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"hive_path\" on \"parse_registry\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"parse_registry\" takes a path parameter \"hive_path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "parse_registry",
"field": "inputSchema.properties.hive_path"
},
"data": {
"param": "hive_path"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"plugins_dir\" on \"parse_registry\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"parse_registry\" takes a path parameter \"plugins_dir\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "parse_registry",
"field": "inputSchema.properties.plugins_dir"
},
"data": {
"param": "plugins_dir"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"j_path\" on \"parse_usnjrnl\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"parse_usnjrnl\" takes a path parameter \"j_path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "parse_usnjrnl",
"field": "inputSchema.properties.j_path"
},
"data": {
"param": "j_path"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"filter_path\" on \"parse_usnjrnl\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"parse_usnjrnl\" takes a path parameter \"filter_path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "parse_usnjrnl",
"field": "inputSchema.properties.filter_path"
},
"data": {
"param": "filter_path"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"plaso_path\" on \"plaso_supertimeline\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"plaso_supertimeline\" takes a path parameter \"plaso_path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "plaso_supertimeline",
"field": "inputSchema.properties.plaso_path"
},
"data": {
"param": "plaso_path"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"memdump_path\" on \"vol3_query\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"vol3_query\" takes a path parameter \"memdump_path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "vol3_query",
"field": "inputSchema.properties.memdump_path"
},
"data": {
"param": "memdump_path"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"evtx_path\" on \"oath_verify_claim\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"oath_verify_claim\" takes a path parameter \"evtx_path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "oath_verify_claim",
"field": "inputSchema.properties.evtx_path"
},
"data": {
"param": "evtx_path"
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (src/oath/mcp/tools/find_strings_on_image.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`src/oath/mcp/tools/find_strings_on_image.py:112`): 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/oath/mcp/tools/find_strings_on_image.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/oath/mcp/tools/find_strings_on_image.py",
"line": 112
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (src/oath/mcp/tools/parse_evtx.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`src/oath/mcp/tools/parse_evtx.py:135`): 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/oath/mcp/tools/parse_evtx.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/oath/mcp/tools/parse_evtx.py",
"line": 135
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "oath_mount",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"parameter \"path\""
]
}
},
{
"tool": "oath_list_handles",
"tags": [],
"reasons": {}
},
{
"tool": "oath_list_envelopes",
"tags": [],
"reasons": {}
},
{
"tool": "oath_read_envelope",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"read_env\""
]
}
},
{
"tool": "parse_evtx",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"parameter \"path\""
]
}
},
{
"tool": "parse_mft",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"parameter \"path\""
]
}
},
{
"tool": "parse_amcache",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"parameter \"path\""
]
}
},
{
"tool": "parse_prefetch",
"tags": [],
"reasons": {}
},
{
"tool": "run_hayabusa",
"tags": [],
"reasons": {}
},
{
"tool": "parse_registry",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"parameter \"path\""
]
}
},
{
"tool": "parse_usnjrnl",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"parameter \"path\""
]
}
},
{
"tool": "plaso_supertimeline",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"parameter \"path\""
]
}
},
{
"tool": "vol3_query",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"parameter \"path\""
]
}
},
{
"tool": "find_strings_on_image",
"tags": [],
"reasons": {}
},
{
"tool": "enumerate_credential_artifacts",
"tags": [],
"reasons": {}
},
{
"tool": "oath_verify_claim",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"parameter \"path\""
]
}
}
],
"surfaceDigest": "ff5d17d95ac84161a664b76d4e6f61f7174cdf0a5ca99bb654b052ed4a82cd80",
"stats": {
"tools": 16,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 3,
"medium": 0,
"low": 14,
"info": 0
}
}
}