GitHub (mcp-github-server) — 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": "mcp-github-server",
"source": {
"kind": "package",
"origin": "mcp-github-server"
},
"server": {
"name": "mcp-github-server"
}
},
"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": [
"can send data / act on an external service",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)"
],
"tags": [
"external-sink",
"sensitive-source"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (40 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-003",
"title": "Read-and-egress in one tool: \"create_webhook\"",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "Tool \"create_webhook\" can both read sensitive data and send data to an external destination. Even without an explicit untrusted-input leg, this is a single-call data-exfiltration path if the model is ever manipulated.",
"remediation": "Separate reading from sending; require explicit user confirmation before egress of file/secret contents.",
"location": {
"kind": "flow",
"name": "create_webhook"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"tags": [
"external-sink",
"sensitive-source"
]
}
},
{
"ruleId": "MTC-FLOW-003",
"title": "Read-and-egress in one tool: \"update_webhook\"",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "Tool \"update_webhook\" can both read sensitive data and send data to an external destination. Even without an explicit untrusted-input leg, this is a single-call data-exfiltration path if the model is ever manipulated.",
"remediation": "Separate reading from sending; require explicit user confirmation before egress of file/secret contents.",
"location": {
"kind": "flow",
"name": "update_webhook"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"tags": [
"external-sink",
"sensitive-source"
]
}
},
{
"ruleId": "MTC-FLOW-004",
"title": "Sensitive-source and external-sink co-exist",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "Tools that read sensitive data ([create_webhook, update_webhook]) and tools that can send data out ([create_issue, create_pull_request, create_webhook, update_webhook, delete_webhook, ping_webhook]) are exposed together. An agent can move private data to the sink.",
"remediation": "Keep secret-reading and egress capabilities on separate, separately-approved servers.",
"location": {
"kind": "flow",
"name": "create_webhook → create_issue"
},
"evidence": "sources [create_webhook, update_webhook] → sinks [create_issue, create_pull_request, create_webhook, update_webhook, delete_webhook, ping_webhook]",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"sources": [
"create_webhook",
"update_webhook"
],
"sinks": [
"create_issue",
"create_pull_request",
"create_webhook",
"update_webhook",
"delete_webhook",
"ping_webhook"
]
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url\" on \"create_webhook\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"create_webhook\" takes a URL/host parameter \"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": "create_webhook",
"field": "inputSchema.properties.url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url"
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url\" on \"update_webhook\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"update_webhook\" takes a URL/host parameter \"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": "update_webhook",
"field": "inputSchema.properties.url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"create_webhook"
],
"externalSink": [
"create_webhook"
],
"selfContained": true,
"description": "Tool \"create_webhook\" both reads sensitive data and can send it externally."
},
{
"id": "flow-2",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"update_webhook"
],
"externalSink": [
"update_webhook"
],
"selfContained": true,
"description": "Tool \"update_webhook\" both reads sensitive data and can send it externally."
},
{
"id": "flow-3",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"create_webhook",
"update_webhook"
],
"externalSink": [
"create_issue",
"create_pull_request",
"create_webhook",
"update_webhook",
"delete_webhook",
"ping_webhook"
],
"selfContained": false,
"path": [
"create_webhook",
"create_issue"
],
"pathWired": true,
"description": "A sensitive-source → external-sink chain exists: create_webhook ⇒ create_issue."
}
],
"capabilities": [
{
"tool": "list_repositories",
"tags": [],
"reasons": {}
},
{
"tool": "get_repository",
"tags": [],
"reasons": {}
},
{
"tool": "list_issues",
"tags": [],
"reasons": {}
},
{
"tool": "list_pull_requests",
"tags": [],
"reasons": {}
},
{
"tool": "list_branches",
"tags": [],
"reasons": {}
},
{
"tool": "protect_branch",
"tags": [],
"reasons": {}
},
{
"tool": "get_commit",
"tags": [],
"reasons": {}
},
{
"tool": "list_commits",
"tags": [],
"reasons": {}
},
{
"tool": "compare_commits",
"tags": [],
"reasons": {}
},
{
"tool": "get_file_content",
"tags": [],
"reasons": {}
},
{
"tool": "search_repositories",
"tags": [],
"reasons": {}
},
{
"tool": "search_code",
"tags": [],
"reasons": {}
},
{
"tool": "search_issues",
"tags": [],
"reasons": {}
},
{
"tool": "search_users",
"tags": [],
"reasons": {}
},
{
"tool": "search_commits",
"tags": [],
"reasons": {}
},
{
"tool": "get_user_info",
"tags": [],
"reasons": {}
},
{
"tool": "create_issue",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"create_issue\""
]
}
},
{
"tool": "update_issue",
"tags": [],
"reasons": {}
},
{
"tool": "close_issue",
"tags": [],
"reasons": {}
},
{
"tool": "add_issue_comment",
"tags": [],
"reasons": {}
},
{
"tool": "list_issue_comments",
"tags": [],
"reasons": {}
},
{
"tool": "create_pull_request",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"create_pull_request\""
]
}
},
{
"tool": "get_pull_request",
"tags": [],
"reasons": {}
},
{
"tool": "merge_pull_request",
"tags": [],
"reasons": {}
},
{
"tool": "close_pull_request",
"tags": [],
"reasons": {}
},
{
"tool": "update_pull_request",
"tags": [],
"reasons": {}
},
{
"tool": "add_pull_request_review",
"tags": [],
"reasons": {}
},
{
"tool": "list_pull_request_reviews",
"tags": [],
"reasons": {}
},
{
"tool": "list_releases",
"tags": [],
"reasons": {}
},
{
"tool": "get_release",
"tags": [],
"reasons": {}
},
{
"tool": "create_release",
"tags": [],
"reasons": {}
},
{
"tool": "list_tags",
"tags": [],
"reasons": {}
},
{
"tool": "create_tag",
"tags": [],
"reasons": {}
},
{
"tool": "list_webhooks",
"tags": [],
"reasons": {}
},
{
"tool": "get_webhook",
"tags": [],
"reasons": {}
},
{
"tool": "create_webhook",
"tags": [
"external-sink",
"sensitive-source"
],
"reasons": {
"external-sink": [
"keyword \"webhook\""
],
"sensitive-source": [
"parameter \"secret\""
]
}
},
{
"tool": "update_webhook",
"tags": [
"external-sink",
"sensitive-source"
],
"reasons": {
"external-sink": [
"keyword \"webhook\""
],
"sensitive-source": [
"parameter \"secret\""
]
}
},
{
"tool": "delete_webhook",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"webhook\""
]
}
},
{
"tool": "ping_webhook",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"webhook\""
]
}
},
{
"tool": "Mis Repositorios",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "e22fa7a802873fe945c6447e940a4c883f6150ab132bf9340ca47f77d0956da7",
"stats": {
"tools": 40,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 3,
"medium": 2,
"low": 0,
"info": 0
}
}
}