Skill Seekers — the complete, unedited output of the deterministic mcptrustchecker engine v1.13.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.13.0",
"methodologyVersion": "mcptrustchecker-1.13"
},
"target": {
"id": "skill-seekers",
"source": {
"kind": "package",
"origin": "skill-seekers"
},
"server": {
"name": "skill-seekers"
}
},
"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-1.13"
},
"capability": {
"level": "high",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"untrusted-input",
"code-exec",
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (19 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-002",
"title": "Shell/command execution in server code (src/skill_seekers/cli/agent_client.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/skill_seekers/cli/agent_client.py:871`): 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/skill_seekers/cli/agent_client.py"
},
"evidence": "result = subprocess.run( cmd, capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/skill_seekers/cli/agent_client.py",
"line": 871,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/skill_seekers/cli/browser_renderer.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/skill_seekers/cli/browser_renderer.py:38`): 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/skill_seekers/cli/browser_renderer.py"
},
"evidence": "try: result = subprocess.run( [sys.executable, \"-m\", \"playwright\", \"install\", \"chromium\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/skill_seekers/cli/browser_renderer.py",
"line": 38,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/skill_seekers/cli/doctor.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/skill_seekers/cli/doctor.py:108`): 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/skill_seekers/cli/doctor.py"
},
"evidence": "try: result = subprocess.run([\"git\", \"--version\"], capture_output=True, text=True, timeout=5) version",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/skill_seekers/cli/doctor.py",
"line": 108,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/skill_seekers/cli/enhance_skill_local.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/skill_seekers/cli/enhance_skill_local.py:234`): 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/skill_seekers/cli/enhance_skill_local.py"
},
"evidence": "n ( subprocess.run( cmd_parts, capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/skill_seekers/cli/enhance_skill_local.py",
"line": 234,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/skill_seekers/cli/github_fetcher.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/skill_seekers/cli/github_fetcher.py:218`): 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/skill_seekers/cli/github_fetcher.py"
},
"evidence": "_dir)] result = subprocess.run(cmd, capture_output=True, text=True) if result.returncode != 0:",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/skill_seekers/cli/github_fetcher.py",
"line": 218,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/skill_seekers/cli/man_scraper.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/skill_seekers/cli/man_scraper.py:397`): 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/skill_seekers/cli/man_scraper.py"
},
"evidence": "y: result = subprocess.run( cmd, capture_output=True, text=T",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/skill_seekers/cli/man_scraper.py",
"line": 397,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/skill_seekers/cli/package_multi.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/skill_seekers/cli/package_multi.py: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": "src/skill_seekers/cli/package_multi.py"
},
"evidence": "try: result = subprocess.run( [sys.executable, str(Path(__file__).parent / \"package_skill.py\"), st",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/skill_seekers/cli/package_multi.py",
"line": 17,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/skill_seekers/cli/signal_collectors.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/skill_seekers/cli/signal_collectors.py:321`): 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/skill_seekers/cli/signal_collectors.py"
},
"evidence": "try: result = subprocess.run( [\"git\", \"-C\", str(root), \"config\", \"--get\", \"remote.origin.url\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/skill_seekers/cli/signal_collectors.py",
"line": 321,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/skill_seekers/cli/unified_scraper.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/skill_seekers/cli/unified_scraper.py:484`): 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/skill_seekers/cli/unified_scraper.py"
},
"evidence": "y: result = subprocess.run( [\"git\", \"clone\", repo_url, clone_path], capture_",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/skill_seekers/cli/unified_scraper.py",
"line": 484,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/skill_seekers/cli/utils.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/skill_seekers/cli/utils.py:58`): 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/skill_seekers/cli/utils.py"
},
"evidence": "(standard) subprocess.run([\"xdg-open\", str(folder_path)], check=True) elif system == \"Darwin\": # m",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/skill_seekers/cli/utils.py",
"line": 58,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (src/skill_seekers/cli/config_command.py)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/skill_seekers/cli/config_command.py:481`): 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/skill_seekers/cli/config_command.py"
},
"evidence": "response = requests.get( \"https://api.github.com/rate_limit\", heade",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "src/skill_seekers/cli/config_command.py",
"line": 481,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"git_url\" on \"fetch_config\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"fetch_config\" takes a URL/host parameter \"git_url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
"remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
"location": {
"kind": "tool",
"name": "fetch_config",
"field": "inputSchema.properties.git_url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "git_url"
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"git_url\" on \"add_config_source\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"add_config_source\" takes a URL/host parameter \"git_url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
"remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
"location": {
"kind": "tool",
"name": "add_config_source",
"field": "inputSchema.properties.git_url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "git_url"
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (src/skill_seekers/cli/doctor.py)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`src/skill_seekers/cli/doctor.py:74`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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/skill_seekers/cli/doctor.py"
},
"evidence": "try: mod = __import__(module_name.split(\".\")[0]) version = getattr(mod, \"__version__\", getattr(mod,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "src/skill_seekers/cli/doctor.py",
"line": 74,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_github_scraper.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_github_scraper.py:924`): 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": "tests/test_github_scraper.py"
},
"evidence": "\") mock_requests.assert_called_once_with( \"https://raw.githubusercontent.com/ccxt/cc",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "tests/test_github_scraper.py",
"line": 924,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_issue_219_e2e.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_issue_219_e2e.py:82`): 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": "tests/test_issue_219_e2e.py"
},
"evidence": "ed mock_requests.assert_called_once_with( \"https://raw.githubusercontent.com/ccxt/cc",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "tests/test_issue_219_e2e.py",
"line": 82,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal in packaging/dev tooling (tests/test_new_source_types.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_new_source_types.py:922`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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_new_source_types.py"
},
"evidence": ".getsource( __import__( \"skill_seekers.cli.create_command\", fromlist=[\"Creat",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "tests/test_new_source_types.py",
"line": 922,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "greet",
"tags": [],
"reasons": {}
},
{
"tool": "generate_config",
"tags": [],
"reasons": {}
},
{
"tool": "list_configs",
"tags": [],
"reasons": {}
},
{
"tool": "validate_config",
"tags": [],
"reasons": {}
},
{
"tool": "estimate_pages",
"tags": [],
"reasons": {}
},
{
"tool": "scrape_docs",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"scrape\""
]
}
},
{
"tool": "scrape_github",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"scrape\""
]
}
},
{
"tool": "scrape_pdf",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"scrape\""
]
}
},
{
"tool": "package_skill",
"tags": [],
"reasons": {}
},
{
"tool": "upload_skill",
"tags": [],
"reasons": {}
},
{
"tool": "install_skill",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "split_config",
"tags": [],
"reasons": {}
},
{
"tool": "generate_router",
"tags": [],
"reasons": {}
},
{
"tool": "fetch_config",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "submit_config",
"tags": [],
"reasons": {}
},
{
"tool": "add_config_source",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "list_config_sources",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "remove_config_source",
"tags": [],
"reasons": {}
},
{
"tool": "extract_config_patterns",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "5af8d2d1e78b5df607b42a939b1d4a80eefbb5fb57ef072b48cf14ea0b20233b",
"stats": {
"tools": 19,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 10,
"medium": 4,
"low": 3,
"info": 0
}
}
}