Runrunit — 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-runrunit",
"source": {
"kind": "package",
"origin": "mcp-runrunit"
},
"server": {
"name": "mcp-runrunit"
}
},
"grade": "A",
"score": {
"score": 94,
"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": "source",
"label": "publisher verification (provenance) — cryptographic build provenance ties the artifact to its source",
"appliedPenalty": 0
},
{
"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": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"untrusted-input",
"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 (34 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-001",
"title": "Dynamic code execution in server code (dist/index.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.js:2942`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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/index.js"
},
"evidence": "const makeValidate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode); const v",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/index.js",
"line": 2942,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/application/git-repo-detect.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/application/git-repo-detect.js:1`): 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/application/git-repo-detect.js"
},
"evidence": "ecFileSync } from 'node:child_process'; import path from 'node:path'; function runGit(cwd, args) { try { con",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/application/git-repo-detect.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/index.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.js:19608`): 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/index.js"
},
"evidence": "ecFileSync } from \"node:child_process\"; import path6 from \"node:path\"; function runGit(cwd, args) { try { const ou",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/index.js",
"line": 19608,
"nonRuntime": false
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([runrunit_get_task]) co-exist with external-action tools ([runrunit_create_comment, runrunit_discord_send_message, runrunit_discord_get_or_create_channel]). 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": "runrunit_get_task → runrunit_create_comment"
},
"evidence": "untrusted [runrunit_get_task] → sinks [runrunit_create_comment, runrunit_discord_send_message, runrunit_discord_get_or_create_channel]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"runrunit_get_task"
],
"sinks": [
"runrunit_create_comment",
"runrunit_discord_send_message",
"runrunit_discord_get_or_create_channel"
]
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url_antes\" on \"runrunit_create_comment\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"runrunit_create_comment\" takes a URL/host parameter \"url_antes\" 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": "runrunit_create_comment",
"field": "inputSchema.properties.url_antes"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url_antes"
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url_depois\" on \"runrunit_create_comment\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"runrunit_create_comment\" takes a URL/host parameter \"url_depois\" 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": "runrunit_create_comment",
"field": "inputSchema.properties.url_depois"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url_depois"
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/server.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/server.js:12`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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/server.js"
},
"evidence": "HTTPServerTransport } = require(streamableHttpPath); const PORT = Number(process.env.MCP_HTTP_PORT) || 3000; const MCP_P",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/server.js",
"line": 12,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"mcp-runrunit\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "mcp-runrunit"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"runrunit_get_task"
],
"sensitiveSource": [],
"externalSink": [
"runrunit_create_comment",
"runrunit_discord_send_message",
"runrunit_discord_get_or_create_channel"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "runrunit_list_projects",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_list_tasks",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_list_task_filters",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_list_board_stages",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_move_task_stage",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_get_task",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "runrunit_get_task_description",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_list_subtasks",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_create_task",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_update_task",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_delete_task",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_create_workflow",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_assignment_play",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_list_task_comments",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_get_comment",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_create_comment",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"create_comment\""
]
}
},
{
"tool": "runrunit_update_comment",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_delete_comment",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_comment_reaction",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_create_external_comment",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_suggest_devs_with_free_queue",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_project_detect_platform",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_list_cursor_catalog",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_get_pr_template",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_install_cursor_skills",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_install_cursor_agents",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_discord_send_message",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "runrunit_discord_create_channel",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_discord_list_channels",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_discord_get_or_create_channel",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "runrunit_share_cursor_agent",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_share_cursor_skill",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_share_cursor_agent_bitbucket",
"tags": [],
"reasons": {}
},
{
"tool": "runrunit_share_cursor_skill_bitbucket",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "a8985356bc2657c8062f4baf41f97a368acbcb4f55729fae762b3478737be967",
"stats": {
"tools": 34,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 3,
"medium": 4,
"low": 0,
"info": 1
}
}
}