Pm Claude Skills — 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": "pm-claude-skills",
"source": {
"kind": "package",
"origin": "pm-claude-skills"
},
"server": {
"name": "pm-claude-skills"
}
},
"grade": "B",
"score": {
"score": 84,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 9.45,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 6.3,
"network": 0,
"hygiene": 0
},
"vector": [
{
"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-SUP-010",
"category": "supply-chain",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
}
],
"gatesFired": [],
"methodologyVersion": "mcptrustchecker-1.4"
},
"capability": {
"level": "high",
"reasons": [
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"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-001",
"title": "Dynamic code execution in server code (skills/tornado-sensitivity/scripts/tornado.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`skills/tornado-sensitivity/scripts/tornado.py:97`): 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": "skills/tornado-sensitivity/scripts/tornado.py"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "skills/tornado-sensitivity/scripts/tornado.py",
"line": 97
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (bin/chain.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/chain.mjs:17`): 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": "bin/chain.mjs"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/chain.mjs",
"line": 17
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (bin/cli.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/cli.mjs:18`): 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": "bin/cli.mjs"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/cli.mjs",
"line": 18
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (bin/lib/scheduler.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/lib/scheduler.mjs:7`): 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": "bin/lib/scheduler.mjs"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/lib/scheduler.mjs",
"line": 7
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (bin/mcp-audit.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/mcp-audit.mjs:20`): 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": "bin/mcp-audit.mjs"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/mcp-audit.mjs",
"line": 20
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (bin/skillpack.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/skillpack.mjs:16`): 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": "bin/skillpack.mjs"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/skillpack.mjs",
"line": 16
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (web/build-skills.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`web/build-skills.mjs:126`): 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": "web/build-skills.mjs"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "web/build-skills.mjs",
"line": 126
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (bin/brief.mjs)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`bin/brief.mjs:78`): 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": "bin/brief.mjs"
},
"evidence": "fetch('https://raw.githubusercontent.com/mohitagw15856/pm-claude-skills/vitals-data/history.json'",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "bin/brief.mjs",
"line": 78
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (bin/install.mjs)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`bin/install.mjs:42`): 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": "bin/install.mjs"
},
"evidence": "fetch('https://api.github.com'",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "bin/install.mjs",
"line": 42
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (bin/lib/providers.mjs)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`bin/lib/providers.mjs:12`): 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": "bin/lib/providers.mjs"
},
"evidence": "fetch('https://api.anthropic.com/v1/messages'",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "bin/lib/providers.mjs",
"line": 12
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (web/app.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`web/app.js:273`): 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": "web/app.js"
},
"evidence": "fetch('https://api.github.com/repos/mohitagw15856/pm-claude-skills'",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "web/app.js",
"line": 273
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (bin/cli.mjs)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`bin/cli.mjs:354`): 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": "bin/cli.mjs"
},
"evidence": "execSync(`git log --pretty=format:\"%as %h %s\" -- \"skills/${",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "bin/cli.mjs",
"line": 354
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (bin/lib/scheduler.mjs)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`bin/lib/scheduler.mjs:38`): 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": "bin/lib/scheduler.mjs"
},
"evidence": "execSync(`launchctl unload ${",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "bin/lib/scheduler.mjs",
"line": 38
}
},
{
"ruleId": "MTC-SUP-010",
"title": "Package runs install-time scripts (postinstall)",
"category": "supply-chain",
"severity": "medium",
"confidence": "strong",
"description": "\"pm-claude-skills\" executes postinstall script(s) at install time. The large majority of malicious packages abuse install hooks to run code before you ever import them.",
"remediation": "Review the scripts; install with --ignore-scripts where possible and vet what they do.",
"location": {
"kind": "package",
"name": "pm-claude-skills"
},
"owasp": "LLM03:2025 Supply Chain",
"references": [
"https://github.com/ossf/package-analysis",
"https://owasp.org/www-project-top-10-ci-cd-security-risks/"
],
"data": {
"scripts": [
"postinstall"
]
}
}
],
"toxicFlows": [],
"capabilities": [],
"surfaceDigest": "932a0de691599c68a32f0fa8d3157886f120a8e5dd41352a11e1a097e2ca5c73",
"stats": {
"tools": 0,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 7,
"medium": 7,
"low": 0,
"info": 0
}
}
}