Github Agent — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "mcp-github-agent",
"source": {
"kind": "package",
"origin": "mcp-github-agent"
},
"server": {
"name": "mcp-github-agent"
}
},
"grade": "B",
"score": {
"score": 89,
"threatScore": 100,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "client",
"term": "capability-exposure",
"level": "critical",
"label": "capability blast radius (critical) — client exposure if the model is manipulated",
"appliedPenalty": 10
},
{
"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-1.9"
},
"capability": {
"level": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"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",
"untrusted-input, sensitive-source and egress co-exist across tools (toxic-flow surface)",
"untrusted input can reach code execution"
],
"tags": [
"untrusted-input",
"sensitive-source",
"external-sink",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (12 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-FLOW-002",
"title": "Completed toxic-flow trifecta across tools",
"category": "exfiltration",
"severity": "critical",
"confidence": "strong",
"description": "This server (without client built-ins) exposes a complete data-exfiltration chain: comment_pr_review → get_file_contents → create_issue. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.",
"remediation": "Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.",
"location": {
"kind": "flow",
"name": "comment_pr_review → get_file_contents → create_issue"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"untrusted": [
"comment_pr_review"
],
"sources": [
"get_file_contents"
],
"sinks": [
"create_issue"
],
"path": [
"comment_pr_review",
"get_file_contents",
"create_issue"
],
"edges": [
{
"from": "comment_pr_review",
"to": "get_file_contents",
"kind": "agent-mediated"
},
{
"from": "get_file_contents",
"to": "create_issue",
"kind": "agent-mediated"
}
],
"wired": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/analyzers/ruff.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/analyzers/ruff.py:21`): 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/analyzers/ruff.py"
},
"evidence": "y: result = subprocess.run( [self.cmd, \"check\", \"--output-format\", \"json\", str(path)],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/analyzers/ruff.py",
"line": 21,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_http_transport.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_http_transport.py:53`): 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": "tests/test_http_transport.py"
},
"evidence": "-token\"} proc = subprocess.Popen( [sys.executable, \"-m\", \"src.main\", \"--transport\", \"http\", \"--port\"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_http_transport.py",
"line": 53,
"nonRuntime": true
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "critical",
"confidence": "strong",
"untrustedInput": [
"comment_pr_review"
],
"sensitiveSource": [
"get_file_contents"
],
"externalSink": [
"create_issue"
],
"selfContained": false,
"path": [
"comment_pr_review",
"get_file_contents",
"create_issue"
],
"pathWired": false,
"description": "A cross-tool exfiltration chain exists: comment_pr_review → get_file_contents → create_issue."
}
],
"capabilities": [
{
"tool": "search_code",
"tags": [],
"reasons": {}
},
{
"tool": "list_issues",
"tags": [],
"reasons": {}
},
{
"tool": "get_pr_diff",
"tags": [],
"reasons": {}
},
{
"tool": "review_pr_diff",
"tags": [],
"reasons": {}
},
{
"tool": "comment_pr_review",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "get_file_contents",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"get_file_contents\""
]
}
},
{
"tool": "create_issue",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"create_issue\""
]
}
},
{
"tool": "create_pr",
"tags": [],
"reasons": {}
},
{
"tool": "create_or_update_file",
"tags": [],
"reasons": {}
},
{
"tool": "push_files",
"tags": [],
"reasons": {}
},
{
"tool": "add_issue_comment",
"tags": [],
"reasons": {}
},
{
"tool": "merge_pull_request",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "6537ea282504cfe4c559ef8694df9f7ced3be2c00ab969eeda05fd52de0f12c3",
"stats": {
"tools": 12,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 1,
"high": 1,
"medium": 0,
"low": 1,
"info": 0
}
}
}