Agent Twitter Client — 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": "agent-twitter-client-mcp",
"source": {
"kind": "package",
"origin": "agent-twitter-client-mcp"
},
"server": {
"name": "agent-twitter-client-mcp"
}
},
"grade": "A",
"score": {
"score": 96,
"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": "moderate",
"label": "capability blast radius (moderate) — client exposure if the model is manipulated",
"appliedPenalty": 3
},
{
"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": "moderate",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service"
],
"tags": [
"untrusted-input",
"external-sink"
]
},
"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-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([get_user_tweets, get_tweet_by_id]) co-exist with external-action tools ([send_tweet, send_tweet_with_poll, like_tweet, retweet, quote_tweet]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.",
"remediation": "Require confirmation for state-changing/egress actions triggered after processing untrusted content.",
"location": {
"kind": "flow",
"name": "get_user_tweets → send_tweet"
},
"evidence": "untrusted [get_user_tweets, get_tweet_by_id] → sinks [send_tweet, send_tweet_with_poll, like_tweet, retweet, quote_tweet]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"get_user_tweets",
"get_tweet_by_id"
],
"sinks": [
"send_tweet",
"send_tweet_with_poll",
"like_tweet",
"retweet",
"quote_tweet"
]
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (build/twitter-client.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`build/twitter-client.js:261`): 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": "build/twitter-client.js"
},
"evidence": "rsationResponse = await fetch('https://x.com/i/api/graphql/6cmfJY3d7EPWuCSXWrkOFg/CreateGrokConversation', {",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "build/twitter-client.js",
"line": 261,
"nonRuntime": false
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"get_user_tweets",
"get_tweet_by_id"
],
"sensitiveSource": [],
"externalSink": [
"send_tweet",
"send_tweet_with_poll",
"like_tweet",
"retweet",
"quote_tweet"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "get_user_tweets",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "get_tweet_by_id",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "search_tweets",
"tags": [],
"reasons": {}
},
{
"tool": "send_tweet",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"tweet\""
]
}
},
{
"tool": "send_tweet_with_poll",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"tweet\""
]
}
},
{
"tool": "like_tweet",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"tweet\""
]
}
},
{
"tool": "retweet",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"tweet\""
]
}
},
{
"tool": "quote_tweet",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"tweet\""
]
}
},
{
"tool": "get_user_profile",
"tags": [],
"reasons": {}
},
{
"tool": "follow_user",
"tags": [],
"reasons": {}
},
{
"tool": "get_followers",
"tags": [],
"reasons": {}
},
{
"tool": "get_following",
"tags": [],
"reasons": {}
},
{
"tool": "grok_chat",
"tags": [],
"reasons": {}
},
{
"tool": "health_check",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "929ff991e41d0f3ec7e8cae6bc04a8a4f9a917b56cff0672dd3a14fb49dbdfb9",
"stats": {
"tools": 14,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 0,
"medium": 2,
"low": 0,
"info": 0
}
}
}