Iris — 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": "@jenova-marie/iris-mcp",
"source": {
"kind": "package",
"origin": "@jenova-marie/iris-mcp"
},
"server": {
"name": "@jenova-marie/iris-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",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"external-sink",
"sensitive-source",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (20 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-004",
"title": "Sensitive-source and external-sink co-exist",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "Tools that read sensitive data ([get_logs]) and tools that can send data out ([send_message]) 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": "get_logs → send_message"
},
"evidence": "sources [get_logs] → sinks [send_message]",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"sources": [
"get_logs"
],
"sinks": [
"send_message"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/actions/fork.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/actions/fork.js:18`): 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/actions/fork.js"
},
"evidence": "port { execSync } from \"child_process\"; import { existsSync } from \"fs\"; import { resolve } from \"path\"; import { getIri",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/actions/fork.js",
"line": 18,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/agents/template-utils.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/agents/template-utils.js:5`): 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/agents/template-utils.js"
},
"evidence": "port { execSync } from \"child_process\"; import { access } from \"fs/promises\"; import { join } from \"path\"; import { home",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/agents/template-utils.js",
"line": 5,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/process-pool/claude-process.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/process-pool/claude-process.js:216`): 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/process-pool/claude-process.js"
},
"evidence": "nfig) */ async spawn(spawnCacheEntry, spawnTimeout = 20000) { this.logger.info({ teamName:",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/process-pool/claude-process.js",
"line": 216,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/transport/local-transport.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/transport/local-transport.js:7`): 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/transport/local-transport.js"
},
"evidence": "import { spawn } from \"child_process\"; import { BehaviorSubject, Subject, firstValueFrom } from \"rxjs\"; import { filter",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/transport/local-transport.js",
"line": 7,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/transport/ssh-transport.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/transport/ssh-transport.js:17`): 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/transport/ssh-transport.js"
},
"evidence": "import { spawn } from \"child_process\"; import { BehaviorSubject, Subject, firstValueFrom, filter, take, timeout, } from",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/transport/ssh-transport.js",
"line": 17,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/utils/claude-print.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/utils/claude-print.js:13`): 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/utils/claude-print.js"
},
"evidence": "import { spawn } from \"child_process\"; import { getChildLogger } from \"./logger.js\"; import { TimeoutError } from \"./er",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/utils/claude-print.js",
"line": 13,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/utils/mcp-config-writer.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/utils/mcp-config-writer.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": "dist/utils/mcp-config-writer.js"
},
"evidence": "import { spawn } from \"child_process\"; import { fileURLToPath } from \"url\"; import { dirname, join } from \"path\"; impor",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/utils/mcp-config-writer.js",
"line": 8,
"nonRuntime": false
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"get_logs"
],
"externalSink": [
"send_message"
],
"selfContained": false,
"path": [
"get_logs",
"send_message"
],
"pathWired": true,
"description": "A sensitive-source → external-sink chain exists: get_logs ⇒ send_message."
}
],
"capabilities": [
{
"tool": "send_message",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "quick_message",
"tags": [],
"reasons": {}
},
{
"tool": "ask_message",
"tags": [],
"reasons": {}
},
{
"tool": "session_reboot",
"tags": [],
"reasons": {}
},
{
"tool": "session_delete",
"tags": [],
"reasons": {}
},
{
"tool": "session_fork",
"tags": [],
"reasons": {}
},
{
"tool": "team_status",
"tags": [],
"reasons": {}
},
{
"tool": "team_wake",
"tags": [],
"reasons": {}
},
{
"tool": "team_launch",
"tags": [],
"reasons": {}
},
{
"tool": "team_sleep",
"tags": [],
"reasons": {}
},
{
"tool": "team_wake_all",
"tags": [],
"reasons": {}
},
{
"tool": "session_report",
"tags": [],
"reasons": {}
},
{
"tool": "session_cancel",
"tags": [],
"reasons": {}
},
{
"tool": "list_teams",
"tags": [],
"reasons": {}
},
{
"tool": "get_logs",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"get_logs\""
]
}
},
{
"tool": "permissions__approve",
"tags": [],
"reasons": {}
},
{
"tool": "get_date",
"tags": [],
"reasons": {}
},
{
"tool": "get_agent",
"tags": [],
"reasons": {}
},
{
"tool": "projectPath",
"tags": [],
"reasons": {}
},
{
"tool": "includeGitDiff",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "3dfcfe5dfa4a83cb87be733d8cc73e1b97748e8fa3a0cf06a4859f511f52b7fc",
"stats": {
"tools": 20,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 8,
"medium": 0,
"low": 0,
"info": 0
}
}
}