Linkedin — 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": "@maheidem/linkedin-mcp",
"source": {
"kind": "package",
"origin": "@maheidem/linkedin-mcp"
},
"server": {
"name": "@maheidem/linkedin-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": [
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"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 (58 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 (dist/linkedin-complete-mcp.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/linkedin-complete-mcp.js:45`): 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": "dist/linkedin-complete-mcp.js"
},
"evidence": "require(\"http\"); const child_process_1 = require(\"child_process\"); const simple_token_manager_js_1 = require(\"./simple-",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/linkedin-complete-mcp.js",
"line": 45,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/oauth-setup.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/oauth-setup.js:50`): 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": "dist/oauth-setup.js"
},
"evidence": "(require(\"url\")); const child_process_1 = require(\"child_process\"); const inquirer_1 = __importDefault(require(\"inquirer",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/oauth-setup.js",
"line": 50,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/api/linkedin-client.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/api/linkedin-client.js:89`): 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": "dist/api/linkedin-client.js"
},
"evidence": "const response = await fetch('https://www.linkedin.com/oauth/v2/accessToken', { method: 'POST',",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/api/linkedin-client.js",
"line": 89,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/linkedin-basic-mcp.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/linkedin-basic-mcp.js:303`): 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": "dist/linkedin-basic-mcp.js"
},
"evidence": "const response = await fetch('https://api.linkedin.com/v2', { method: 'GET', }); tests.push",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/linkedin-basic-mcp.js",
"line": 303,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/linkedin-complete-mcp-v2.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/linkedin-complete-mcp-v2.js:405`): 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": "dist/linkedin-complete-mcp-v2.js"
},
"evidence": "st userResponse = await fetch('https://api.linkedin.com/v2/userinfo', { headers: { 'Authoriz",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/linkedin-complete-mcp-v2.js",
"line": 405,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/linkedin-complete-mcp.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/linkedin-complete-mcp.js:250`): 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": "dist/linkedin-complete-mcp.js"
},
"evidence": "const response = await fetch('https://www.linkedin.com/oauth/v2/accessToken', { method: 'POST', headers",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/linkedin-complete-mcp.js",
"line": 250,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/linkedin-working-mcp.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/linkedin-working-mcp.js:190`): 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": "dist/linkedin-working-mcp.js"
},
"evidence": "const response = await fetch('https://www.linkedin.com/oauth/v2/accessToken', { method: 'POST', headers",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/linkedin-working-mcp.js",
"line": 190,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/oauth-setup.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/oauth-setup.js:266`): 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": "dist/oauth-setup.js"
},
"evidence": "const response = await fetch('https://www.linkedin.com/oauth/v2/accessToken', { method: 'POST',",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/oauth-setup.js",
"line": 266,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint in packaging/dev tooling (examples/post-to-linkedin.js)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`examples/post-to-linkedin.js:31`): 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": "examples/post-to-linkedin.js"
},
"evidence": "st userResponse = await fetch('https://api.linkedin.com/v2/userinfo', { headers: { 'Authorization': `Beare",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "examples/post-to-linkedin.js",
"line": 31,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (examples/get-linkedin-token.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`examples/get-linkedin-token.js:3`): 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": "examples/get-linkedin-token.js"
},
"evidence": "st { spawn } = require('child_process'); const readline = require('readline'); async function getLinkedInToken() { co",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "examples/get-linkedin-token.js",
"line": 3,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (examples/linkedin-mcp-demo.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`examples/linkedin-mcp-demo.js:3`): 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": "examples/linkedin-mcp-demo.js"
},
"evidence": "st { spawn } = require('child_process'); async function callLinkedIn(toolName, args = {}) { const process = spawn('np",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "examples/linkedin-mcp-demo.js",
"line": 3,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (examples/linkedin-oauth-complete.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`examples/linkedin-oauth-complete.js:3`): 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": "examples/linkedin-oauth-complete.js"
},
"evidence": "st { spawn } = require('child_process'); const http = require('http'); const url = require('url'); const { execSync } =",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "examples/linkedin-oauth-complete.js",
"line": 3,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (examples/linkedin-oauth-debug.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`examples/linkedin-oauth-debug.js:3`): 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": "examples/linkedin-oauth-debug.js"
},
"evidence": "st { spawn } = require('child_process'); const http = require('http'); const url = require('url'); const { execSync } =",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "examples/linkedin-oauth-debug.js",
"line": 3,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (examples/linkedin-oauth-local.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`examples/linkedin-oauth-local.js:3`): 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": "examples/linkedin-oauth-local.js"
},
"evidence": "st { spawn } = require('child_process'); const http = require('http'); const url = require('url'); const { execSync } =",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "examples/linkedin-oauth-local.js",
"line": 3,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (examples/linkedin-success.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`examples/linkedin-success.js:8`): 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": "examples/linkedin-success.js"
},
"evidence": "st { spawn } = require('child_process'); const http = require('http'); const url = require('url'); const { execSync } =",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "examples/linkedin-success.js",
"line": 8,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "generate_summary",
"tags": [],
"reasons": {}
},
{
"tool": "create_update_guide",
"tags": [],
"reasons": {}
},
{
"tool": "track_updates",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_oauth_get_auth_url",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_oauth_exchange_code",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_oauth_refresh_token",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_people_get_profile",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_people_search_members",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_organizations_get_company",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_organizations_get_follower_stats",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_posts_create",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_posts_get",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_posts_update",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_posts_delete",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_ugc_create",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_assets_upload",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_assets_get_upload_url",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_social_actions_like",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_social_actions_comment",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_social_actions_share",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_ads_create_campaign",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_ads_get_campaigns",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_ads_update_campaign",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_ads_get_analytics",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_ads_get_targeting_facets",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_jobs_post",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_jobs_search",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_talent_unified_search",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_learning_get_courses",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_learning_get_classifications",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_messaging_send_message",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "linkedin_messaging_get_conversations",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_events_create",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_events_get",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_sales_navigator_profile_association",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_compliance_get_events",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_get_rate_limits",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_get_api_health",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_get_auth_url",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_exchange_code",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_get_profile",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_create_post",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_test_connection",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_authenticate",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_check_auth",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_logout",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_get_user_info",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_create_optimized_post",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_analyze_profile_from_data",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_generate_optimized_content",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_post_profile_update",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_get_user_posts",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_get_feed",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_get_post_details",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_get_post_comments",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_get_user_activity",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_auto_auth",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_request_profile_api_access",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "8189d6a20a7a48a0199fe3e39a83302f0c5d6223b63430232595718eb3ba64aa",
"stats": {
"tools": 58,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 2,
"medium": 6,
"low": 7,
"info": 0
}
}
}