Agentic Store — 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": "agentic-store-mcp",
"source": {
"kind": "package",
"origin": "agentic-store-mcp"
},
"server": {
"name": "agentic-store-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-1.13"
},
"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": 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 (agentic_store_mcp/modules/code/security/repo_scanner/handler.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`agentic_store_mcp/modules/code/security/repo_scanner/handler.py:114`): 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": "agentic_store_mcp/modules/code/security/repo_scanner/handler.py"
},
"evidence": "\".env.backup\", \"id_rsa\", \"id_ed25519\", \"id_dsa\", \"id_ecdsa\", \"credentials.json\", \"service-ac",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "agentic_store_mcp/modules/code/security/repo_scanner/handler.py",
"line": 114,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (agentic_store_mcp/modules/code/security/repo_scanner/test_handler.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`agentic_store_mcp/modules/code/security/repo_scanner/test_handler.py:53`): 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": "agentic_store_mcp/modules/code/security/repo_scanner/test_handler.py"
},
"evidence": "make_file(tmp_path, \"id_rsa.txt\", \"-----BEGIN RSA PRIVATE KEY-----\\nMIIEo...\") result = run({\"path\": str(tmp_path",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "agentic_store_mcp/modules/code/security/repo_scanner/test_handler.py",
"line": 53,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (agentic_store_mcp/firewall/ca_manager.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`agentic_store_mcp/firewall/ca_manager.py:33`): 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": "agentic_store_mcp/firewall/ca_manager.py"
},
"evidence": "enerated() result = subprocess.run( [\"security\", \"add-trusted-cert\", \"-r\", \"trustRoot\", str(cert_path)],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "agentic_store_mcp/firewall/ca_manager.py",
"line": 33,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (agentic_store_mcp/firewall/system_proxy.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`agentic_store_mcp/firewall/system_proxy.py:12`): 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": "agentic_store_mcp/firewall/system_proxy.py"
},
"evidence": "list[str]: result = subprocess.run( [\"networksetup\", \"-listallnetworkservices\"], capture_output=True",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "agentic_store_mcp/firewall/system_proxy.py",
"line": 12,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (agentic_store_mcp/modules/code/codebase_analysis/analyze_commits/handler.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`agentic_store_mcp/modules/code/codebase_analysis/analyze_commits/handler.py: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": "agentic_store_mcp/modules/code/codebase_analysis/analyze_commits/handler.py"
},
"evidence": "tderr).\"\"\" result = subprocess.run( [\"git\"] + args, cwd=cwd, capture_output=True, te",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "agentic_store_mcp/modules/code/codebase_analysis/analyze_commits/handler.py",
"line": 16,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (agentic_store_mcp/modules/code/codebase_analysis/analyze_commits/test_handler.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`agentic_store_mcp/modules/code/codebase_analysis/analyze_commits/test_handler.py:48`): 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": "agentic_store_mcp/modules/code/codebase_analysis/analyze_commits/test_handler.py"
},
"evidence": "_is_git_repo passes subprocess.run([\"git\", \"init\"], cwd=tmp_path, capture_output=True) subprocess.run([\"git\", \"c",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "agentic_store_mcp/modules/code/codebase_analysis/analyze_commits/test_handler.py",
"line": 48,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (agentic_store_mcp/modules/tools/list_processes/handler.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`agentic_store_mcp/modules/tools/list_processes/handler.py:90`): 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": "agentic_store_mcp/modules/tools/list_processes/handler.py"
},
"evidence": "try: result = subprocess.run( [\"pgrep\", \"-x\", pattern], capture_output=True, text=True",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "agentic_store_mcp/modules/tools/list_processes/handler.py",
"line": 90,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (agentic_store_mcp/server.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`agentic_store_mcp/server.py:357`): 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": "agentic_store_mcp/server.py"
},
"evidence": "rocess try: subprocess.run([\"launchctl\", \"unsetenv\", key], capture_output=True) except Exception:",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "agentic_store_mcp/server.py",
"line": 357,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (agentic_store_mcp/webapp/app.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`agentic_store_mcp/webapp/app.py:468`): 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": "agentic_store_mcp/webapp/app.py"
},
"evidence": "try: result = subprocess.run( [\"lsof\", \"-ti\", f\"tcp:{port}\"], capture_output=True, tex",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "agentic_store_mcp/webapp/app.py",
"line": 468,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (agentic_store_mcp/webapp/clients.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`agentic_store_mcp/webapp/clients.py: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": "agentic_store_mcp/webapp/clients.py"
},
"evidence": "ame}\"} try: subprocess.Popen(c.launch_cmd) # noqa: S603 return {\"ok\": True, \"error\": None} exce",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "agentic_store_mcp/webapp/clients.py",
"line": 107,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (agentic_store_mcp/webapp/run.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`agentic_store_mcp/webapp/run.py: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": "agentic_store_mcp/webapp/run.py"
},
"evidence": "try: result = subprocess.run( [\"lsof\", \"-ti\", f\"tcp:{port}\"], capture_output=True, tex",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "agentic_store_mcp/webapp/run.py",
"line": 18,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (webapp.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`webapp.py:24`): 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": "webapp.py"
},
"evidence": "try: result = subprocess.run( [\"lsof\", \"-ti\", f\"tcp:{port}\"], capture_output=True, tex",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "webapp.py",
"line": 24,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [],
"surfaceDigest": "1984c4cea9f079cd763ad4cca7dc7ddb682bf6b8ac9336421dc2ada301095811",
"stats": {
"tools": 0,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 12,
"medium": 0,
"low": 0,
"info": 0
}
}
}