Seed — 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": "seed-mcp",
"source": {
"kind": "package",
"origin": "seed-mcp"
},
"server": {
"name": "seed-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": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (14 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-006",
"title": "Reads a sensitive credential path or dumps the environment (src/seed_mcp/publishing/seed_quarantine_github_v2.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/seed_mcp/publishing/seed_quarantine_github_v2.py:87`): 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": "src/seed_mcp/publishing/seed_quarantine_github_v2.py"
},
"evidence": "ls_path = Path.home() / \".git-credentials\" credentials_path.write_text(auth_url + \"\\n\") logger.debug(\"Se",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "src/seed_mcp/publishing/seed_quarantine_github_v2.py",
"line": 87,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/seed_mcp/publishing/publishing_pipeline.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/seed_mcp/publishing/publishing_pipeline.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": "src/seed_mcp/publishing/publishing_pipeline.py"
},
"evidence": "y: result = subprocess.run( command, cwd=cwd, capture_outp",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/seed_mcp/publishing/publishing_pipeline.py",
"line": 48,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/seed_mcp/publishing/seed_quarantine_github_v2.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/seed_mcp/publishing/seed_quarantine_github_v2.py:64`): 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/seed_mcp/publishing/seed_quarantine_github_v2.py"
},
"evidence": "y: result = subprocess.run( cmd, cwd=cwd, capture_output=Tru",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/seed_mcp/publishing/seed_quarantine_github_v2.py",
"line": 64,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/seed_mcp/seed_mcp.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/seed_mcp/seed_mcp.py:691`): 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/seed_mcp/seed_mcp.py"
},
"evidence": "round process = subprocess.Popen( cmd, stdout=subprocess.PIPE, stderr=subpro",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/seed_mcp/seed_mcp.py",
"line": 691,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "who_am_i",
"tags": [],
"reasons": {}
},
{
"tool": "how_do_i",
"tags": [],
"reasons": {}
},
{
"tool": "what_do_i_do",
"tags": [],
"reasons": {}
},
{
"tool": "add_to_seed",
"tags": [],
"reasons": {}
},
{
"tool": "recite_mantra",
"tags": [],
"reasons": {}
},
{
"tool": "parse_qa_json",
"tags": [],
"reasons": {}
},
{
"tool": "ingest_qa_to_carton",
"tags": [],
"reasons": {}
},
{
"tool": "list_available_qa_files",
"tags": [],
"reasons": {}
},
{
"tool": "show_seed_publishing_interface",
"tags": [],
"reasons": {}
},
{
"tool": "refresh_seed_membership_site",
"tags": [],
"reasons": {}
},
{
"tool": "start_publishing_webserver",
"tags": [],
"reasons": {}
},
{
"tool": "home",
"tags": [],
"reasons": {}
},
{
"tool": "list_recently_plotted_courses",
"tags": [],
"reasons": {}
},
{
"tool": "get_publishing_webserver_status",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "63b78ee9fcbb57e46d2febc87511cd3d5d83aad8b6ac846d1a0340641064f1f8",
"stats": {
"tools": 14,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 0,
"low": 0,
"info": 0
}
}
}