Agent Outbound — 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": "agent-outbound",
"source": {
"kind": "package",
"origin": "agent-outbound"
},
"server": {
"name": "agent-outbound"
}
},
"grade": "C",
"score": {
"score": 77,
"grade": "C",
"band": "C",
"categorySubtotals": {
"injection": 11.66,
"exfiltration": 0,
"permissions": 11.66,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.5,
"appliedPenalty": 3.15
},
{
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.25,
"appliedPenalty": 1.58
},
{
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.1,
"appliedPenalty": 0.63
},
{
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.5,
"appliedPenalty": 3.15
},
{
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.25,
"appliedPenalty": 1.58
},
{
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.1,
"appliedPenalty": 0.63
}
],
"gatesFired": [],
"methodologyVersion": "mcptrustchecker-1.4"
},
"capability": {
"level": "moderate",
"reasons": [
"can send data / act on an external service"
],
"tags": [
"external-sink"
]
},
"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-003",
"title": "Hardcoded egress to an external endpoint (dist/orchestrator/runtime/anthropic.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/orchestrator/runtime/anthropic.js:6`): 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": "dist/orchestrator/runtime/anthropic.js"
},
"evidence": "fetch('https://api.anthropic.com/v1/models'",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/orchestrator/runtime/anthropic.js",
"line": 6
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (src/orchestrator/runtime/anthropic.ts)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/orchestrator/runtime/anthropic.ts:6`): 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": "src/orchestrator/runtime/anthropic.ts"
},
"evidence": "fetch('https://api.anthropic.com/v1/models'",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "src/orchestrator/runtime/anthropic.ts",
"line": 6
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/orchestrator/lib/step-cleanup.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/orchestrator/lib/step-cleanup.js:135`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. 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": "dist/orchestrator/lib/step-cleanup.js"
},
"evidence": "exec(`ALTER TABLE records DROP COLUMN ${",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/orchestrator/lib/step-cleanup.js",
"line": 135
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/orchestrator/runtime/db.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/orchestrator/runtime/db.js:919`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. 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": "dist/orchestrator/runtime/db.js"
},
"evidence": "exec(`ALTER TABLE records ADD COLUMN ${column} ${type} DEFAULT ${",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/orchestrator/runtime/db.js",
"line": 919
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (src/orchestrator/lib/step-cleanup.ts)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/orchestrator/lib/step-cleanup.ts:152`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. 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/orchestrator/lib/step-cleanup.ts"
},
"evidence": "exec(`ALTER TABLE records DROP COLUMN ${",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "src/orchestrator/lib/step-cleanup.ts",
"line": 152
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (src/orchestrator/runtime/db.ts)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/orchestrator/runtime/db.ts:925`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. 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/orchestrator/runtime/db.ts"
},
"evidence": "exec(`ALTER TABLE records ADD COLUMN ${column} ${type} DEFAULT ${",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "src/orchestrator/runtime/db.ts",
"line": 925
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (dist/commands/index.js)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/commands/index.js:86`): 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": "dist/commands/index.js"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "dist/commands/index.js",
"line": 86
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (dist/orchestrator/lib/config.js)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/orchestrator/lib/config.js:18`): 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": "dist/orchestrator/lib/config.js"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "dist/orchestrator/lib/config.js",
"line": 18
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (src/commands/index.ts)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/commands/index.ts:114`): 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": "src/commands/index.ts"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "src/commands/index.ts",
"line": 114
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (src/orchestrator/lib/config.ts)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/orchestrator/lib/config.ts:21`): 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": "src/orchestrator/lib/config.ts"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "src/orchestrator/lib/config.ts",
"line": 21
}
}
],
"toxicFlows": [],
"capabilities": [],
"surfaceDigest": "d1f63ac7559911012585700376797cc10a6aeb7a54a07c1b1b7abe6be2d459a4",
"stats": {
"tools": 0,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 0,
"medium": 10,
"low": 0,
"info": 0
}
}
}