Ironward — 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": "ironward",
"source": {
"kind": "package",
"origin": "ironward"
},
"server": {
"name": "ironward"
}
},
"grade": "F",
"score": {
"score": 22,
"grade": "F",
"band": "F",
"gateCap": "D",
"categorySubtotals": {
"injection": 44.8,
"exfiltration": 33,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"ruleId": "MTC-SRC-008",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"rawWeight": 22,
"confidenceMult": 1,
"diminishingFactor": 1,
"appliedPenalty": 22
},
{
"ruleId": "MTC-SRC-008",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"rawWeight": 22,
"confidenceMult": 1,
"diminishingFactor": 0.5,
"appliedPenalty": 11
},
{
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"ruleId": "MTC-SRC-010",
"category": "injection",
"severity": "high",
"confidence": "strong",
"rawWeight": 22,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 15.4
},
{
"ruleId": "MTC-SRC-010",
"category": "injection",
"severity": "high",
"confidence": "strong",
"rawWeight": 22,
"confidenceMult": 0.7,
"diminishingFactor": 0.5,
"appliedPenalty": 7.7
},
{
"ruleId": "MTC-SRC-011",
"category": "injection",
"severity": "high",
"confidence": "strong",
"rawWeight": 22,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 15.4
}
],
"gatesFired": [
"2 confirmed high findings → grade capped at D"
],
"methodologyVersion": "mcptrustchecker-1.4"
},
"capability": {
"level": "high",
"reasons": [
"can send data / act on an external service",
"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",
"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-006",
"title": "Reads a sensitive credential path or dumps the environment (dist/engines/docker-rules.js)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engines/docker-rules.js:112`): 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": "dist/engines/docker-rules.js"
},
"evidence": "id_rsa",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "dist/engines/docker-rules.js",
"line": 112
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (dist/engines/github-rules.js)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engines/github-rules.js:107`): 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": "dist/engines/github-rules.js"
},
"evidence": "id_rsa",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "dist/engines/github-rules.js",
"line": 107
}
},
{
"ruleId": "MTC-SRC-008",
"title": "Hardcoded AWS access key id in server code (dist/commands/benchmark.js)",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"description": "A live-looking AWS access key id is hardcoded in `dist/commands/benchmark.js:203`. 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": "dist/commands/benchmark.js"
},
"evidence": "AWS access key id: AKIA…(redacted)",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"secretType": "aws-access-key",
"file": "dist/commands/benchmark.js",
"line": 203
}
},
{
"ruleId": "MTC-SRC-008",
"title": "Hardcoded JSON Web Token in server code (dist/engines/exploit-generator.js)",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"description": "A live-looking JSON Web Token is hardcoded in `dist/engines/exploit-generator.js:1`. 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": "dist/engines/exploit-generator.js"
},
"evidence": "JSON Web Token: eyJh…(redacted)",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"secretType": "jwt",
"file": "dist/engines/exploit-generator.js",
"line": 1
}
},
{
"ruleId": "MTC-SRC-010",
"title": "Dynamic evaluation of a non-literal value (dist/commands/benchmark.js)",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/commands/benchmark.js:143`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate 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": "dist/commands/benchmark.js"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-010",
"file": "dist/commands/benchmark.js",
"line": 143
}
},
{
"ruleId": "MTC-SRC-010",
"title": "Dynamic evaluation of a non-literal value (dist/engines/code-rules.js)",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engines/code-rules.js:45`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate 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": "dist/engines/code-rules.js"
},
"evidence": "new Function(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-010",
"file": "dist/engines/code-rules.js",
"line": 45
}
},
{
"ruleId": "MTC-SRC-011",
"title": "Assembled command execution and dynamic evaluation in the same server",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "The implementation builds shell commands out of runtime values AND evaluates runtime values as code. Each is a separate arbitrary-execution primitive; a server exposing both gives anything that reaches either one a direct path to running attacker-chosen code.",
"remediation": "Remove the dynamic eval, and pass command arguments as an argv array instead of building a shell string. If both are genuinely required, constrain and validate every value that can reach them.",
"location": {
"kind": "server",
"name": "implementation"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rules": [
"MTC-SRC-009",
"MTC-SRC-010"
]
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/commands/benchmark.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/commands/benchmark.js:143`): 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": "dist/commands/benchmark.js"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/commands/benchmark.js",
"line": 143
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/engines/behavior-analyzer.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engines/behavior-analyzer.js:12`): 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": "dist/engines/behavior-analyzer.js"
},
"evidence": "Function(\"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/engines/behavior-analyzer.js",
"line": 12
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/engines/code-rules.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engines/code-rules.js:34`): 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": "dist/engines/code-rules.js"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/engines/code-rules.js",
"line": 34
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/engines/xss-prefilter.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engines/xss-prefilter.js:66`): 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": "dist/engines/xss-prefilter.js"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/engines/xss-prefilter.js",
"line": 66
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/rules/python.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/rules/python.js:9`): 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": "dist/rules/python.js"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/rules/python.js",
"line": 9
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/rules/react.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/rules/react.js:93`): 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": "dist/rules/react.js"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/rules/react.js",
"line": 93
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/rules/websocket.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/rules/websocket.js:66`): 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": "dist/rules/websocket.js"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/rules/websocket.js",
"line": 66
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/commands/benchmark.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/commands/benchmark.js:291`): 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": "dist/commands/benchmark.js"
},
"evidence": "exec(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/commands/benchmark.js",
"line": 291
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/commands/diff.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/commands/diff.js:1`): 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": "dist/commands/diff.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/commands/diff.js",
"line": 1
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/commands/hooks.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/commands/hooks.js:2`): 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": "dist/commands/hooks.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/commands/hooks.js",
"line": 2
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/commands/login.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/commands/login.js:3`): 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": "dist/commands/login.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/commands/login.js",
"line": 3
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/engines/behavior-analyzer.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engines/behavior-analyzer.js:10`): 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": "dist/engines/behavior-analyzer.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/engines/behavior-analyzer.js",
"line": 10
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/engines/code-rules.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engines/code-rules.js:52`): 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": "dist/engines/code-rules.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/engines/code-rules.js",
"line": 52
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/engines/exploit-generator.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engines/exploit-generator.js:618`): 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": "dist/engines/exploit-generator.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/engines/exploit-generator.js",
"line": 618
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/engines/git-diff.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engines/git-diff.js:1`): 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": "dist/engines/git-diff.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/engines/git-diff.js",
"line": 1
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/rules/java.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/rules/java.js:107`): 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": "dist/rules/java.js"
},
"evidence": "exec(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/rules/java.js",
"line": 107
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/rules/python.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/rules/python.js:93`): 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": "dist/rules/python.js"
},
"evidence": "os.system(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/rules/python.js",
"line": 93
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/commands/login.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/commands/login.js:18`): 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/commands/login.js"
},
"evidence": "fetch(\"https://api.anthropic.com/v1/messages\"",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/commands/login.js",
"line": 18
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/engines/dep-intel.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/engines/dep-intel.js:342`): 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/engines/dep-intel.js"
},
"evidence": "fetch(`https://registry.npmjs.org/${encodeURIComponent(name)}`",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/engines/dep-intel.js",
"line": 342
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/engines/exploit-generator.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/engines/exploit-generator.js:332`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/engines/exploit-generator.js"
},
"evidence": "requests.post('https://yourapp.com${c.endpoint}'",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/engines/exploit-generator.js",
"line": 332
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/commands/benchmark.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/commands/benchmark.js:291`): 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/commands/benchmark.js"
},
"evidence": "exec(\"ls \" +",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/commands/benchmark.js",
"line": 291
}
}
],
"toxicFlows": [],
"capabilities": [],
"surfaceDigest": "5f49c671f916bb8f1663d6ef57bc37d2fae6392549f8d51d7a4530f22a8821ee",
"stats": {
"tools": 0,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 24,
"medium": 4,
"low": 0,
"info": 0
}
}
}