Society Protocol — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "society-protocol",
"source": {
"kind": "package",
"origin": "society-protocol"
},
"server": {
"name": "society-protocol"
}
},
"grade": "D",
"score": {
"score": 68,
"threatScore": 75,
"grade": "D",
"band": "D",
"categorySubtotals": {
"injection": 24.85,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.5,
"appliedPenalty": 3.15
},
{
"kind": "threat",
"ruleId": "MTC-SRC-011",
"category": "injection",
"severity": "high",
"confidence": "strong",
"rawWeight": 22,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 15.4
},
{
"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-1.9"
},
"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 (57 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-010",
"title": "Dynamic evaluation of a non-literal value (dist/skills/engine.js)",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/skills/engine.js:639`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate 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/skills/engine.js"
},
"evidence": "ão!) return eval(expr); } catch { return false; } } buildOpenCla",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-010",
"file": "dist/skills/engine.js",
"line": 639,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-011",
"title": "Assembled command execution and dynamic evaluation in the same server",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "The implementation both builds shell commands out of runtime values (`dist/autoconfig.js`) and evaluates runtime values as code (`dist/skills/engine.js`). Each is a separate arbitrary-execution primitive; a server exposing both gives anything that reaches either one a direct path to running attacker-chosen code. These two sinks are in different files — confirm whether they are actually connected, or are unrelated code paths (e.g. a vendored bundle plus a CLI wrapper).",
"remediation": "Remove the dynamic eval, and pass command arguments as an argv array instead of building a shell string. If both are genuinely required, constrain and validate every value that can reach them.",
"location": {
"kind": "server",
"name": "implementation"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rules": [
"MTC-SRC-009",
"MTC-SRC-010"
],
"commandFile": "dist/autoconfig.js",
"evalFile": "dist/skills/engine.js",
"sameFile": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/skills/engine.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/skills/engine.js:639`): 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/skills/engine.js"
},
"evidence": "ão!) return eval(expr); } catch { return false; } } buildOpenCla",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/skills/engine.js",
"line": 639,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/autoconfig.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/autoconfig.js:14`): 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/autoconfig.js"
},
"evidence": "; import { exec } from 'child_process'; import { detectCloudEnvironment } from './bootstrap.js'; const execAsync = promi",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/autoconfig.js",
"line": 14,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/bootstrap.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/bootstrap.js:15`): 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/bootstrap.js"
},
"evidence": "; import { exec } from 'child_process'; const execAsync = promisify(exec); const REGISTRY_URL = process.env.SOCIETY_REGI",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/bootstrap.js",
"line": 15,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli/commands.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/commands.js:32`): 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/cli/commands.js"
},
"evidence": "cSync } = await import('child_process'); let cmd = 'npx vitest run'; if (options.unit) cmd += ' test/uni",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/commands.js",
"line": 32,
"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:56`): 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": "spawn, execSync } from 'child_process'; import { fileURLToPath } from 'url'; import { resolve } from 'path'; import { re",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/index.js",
"line": 56,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/persona/zkp/engine.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/persona/zkp/engine.js:2`): 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/persona/zkp/engine.js"
},
"evidence": "{ execFileSync } from 'child_process'; import { existsSync, readFileSync } from 'fs'; import { dirname, join } from 'pa",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/persona/zkp/engine.js",
"line": 2,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/skills/engine.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/skills/engine.js:16`): 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/skills/engine.js"
},
"evidence": "import { spawn } from 'child_process'; import { SkillParser } from './parser.js'; export class SkillExecutionError exte",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/skills/engine.js",
"line": 16,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/planner.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/planner.js:243`): 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/planner.js"
},
"evidence": "const response = await fetch('https://api.anthropic.com/v1/messages', { method: 'POST', headers",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/planner.js",
"line": 243,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/skills/engine.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/skills/engine.js:317`): 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/skills/engine.js"
},
"evidence": "const response = await fetch('https://api.anthropic.com/v1/messages', { method: 'POST', headers",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/skills/engine.js",
"line": 317,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/autoconfig.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/autoconfig.js:119`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. 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/autoconfig.js"
},
"evidence": "const { stdout } = exec('df -T ' + path); // Parse output to get filesystem type re",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/autoconfig.js",
"line": 119,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/index.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.js:1653`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. 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": "md) { try { execSync(`command -v ${cmd}`, { stdio: 'ignore' }); return true; } catch {",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/index.js",
"line": 1653,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/compression.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/compression.js:142`): 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/compression.js"
},
"evidence": "eName) { return import(moduleName); } getCompressionStats(original, compressed) { const savings",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/compression.js",
"line": 142,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/persona/embeddings.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/persona/embeddings.js:76`): 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/persona/embeddings.js"
},
"evidence": "w Function('m', 'return import(m)'); const ort = await dynamicImport('onnxruntime-node'); if (!t",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/persona/embeddings.js",
"line": 76,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "society_get_status",
"tags": [],
"reasons": {}
},
{
"tool": "society_join_room",
"tags": [],
"reasons": {}
},
{
"tool": "society_leave_room",
"tags": [],
"reasons": {}
},
{
"tool": "society_list_rooms",
"tags": [],
"reasons": {}
},
{
"tool": "society_get_peers",
"tags": [],
"reasons": {}
},
{
"tool": "society_request_peering",
"tags": [],
"reasons": {}
},
{
"tool": "society_list_peerings",
"tags": [],
"reasons": {}
},
{
"tool": "society_open_bridge",
"tags": [],
"reasons": {}
},
{
"tool": "society_list_bridges",
"tags": [],
"reasons": {}
},
{
"tool": "society_summon",
"tags": [],
"reasons": {}
},
{
"tool": "society_start_mission",
"tags": [],
"reasons": {}
},
{
"tool": "society_pause_mission",
"tags": [],
"reasons": {}
},
{
"tool": "society_resume_mission",
"tags": [],
"reasons": {}
},
{
"tool": "society_stop_mission",
"tags": [],
"reasons": {}
},
{
"tool": "society_list_missions",
"tags": [],
"reasons": {}
},
{
"tool": "society_get_swarm_status",
"tags": [],
"reasons": {}
},
{
"tool": "society_start_research_swarm",
"tags": [],
"reasons": {}
},
{
"tool": "society_list_chains",
"tags": [],
"reasons": {}
},
{
"tool": "society_get_chain",
"tags": [],
"reasons": {}
},
{
"tool": "society_get_pending_steps",
"tags": [],
"reasons": {}
},
{
"tool": "society_submit_step",
"tags": [],
"reasons": {}
},
{
"tool": "society_review_step",
"tags": [],
"reasons": {}
},
{
"tool": "society_cancel_chain",
"tags": [],
"reasons": {}
},
{
"tool": "society_get_reputation",
"tags": [],
"reasons": {}
},
{
"tool": "society_send_message",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "society_list_templates",
"tags": [],
"reasons": {}
},
{
"tool": "society_export_capsule",
"tags": [],
"reasons": {}
},
{
"tool": "persona_add_memory",
"tags": [],
"reasons": {}
},
{
"tool": "persona_search_memories",
"tags": [],
"reasons": {}
},
{
"tool": "persona_query_graph",
"tags": [],
"reasons": {}
},
{
"tool": "persona_update_preference",
"tags": [],
"reasons": {}
},
{
"tool": "persona_issue_capability",
"tags": [],
"reasons": {}
},
{
"tool": "persona_revoke_capability",
"tags": [],
"reasons": {}
},
{
"tool": "persona_attenuate_capability",
"tags": [],
"reasons": {}
},
{
"tool": "persona_issue_claim",
"tags": [],
"reasons": {}
},
{
"tool": "persona_generate_zk_proof",
"tags": [],
"reasons": {}
},
{
"tool": "persona_verify_zk_proof",
"tags": [],
"reasons": {}
},
{
"tool": "persona_share_subgraph",
"tags": [],
"reasons": {}
},
{
"tool": "persona_get_profile",
"tags": [],
"reasons": {}
},
{
"tool": "persona_verify_access_log",
"tags": [],
"reasons": {}
},
{
"tool": "persona_run_retention_sweep",
"tags": [],
"reasons": {}
},
{
"tool": "Persona Profile",
"tags": [],
"reasons": {}
},
{
"tool": "Persona Memory by ID",
"tags": [],
"reasons": {}
},
{
"tool": "Persona Preferences by Category",
"tags": [],
"reasons": {}
},
{
"tool": "Persona Graph by Domain",
"tags": [],
"reasons": {}
},
{
"tool": "Persona Capability by Token",
"tags": [],
"reasons": {}
},
{
"tool": "Persona Active Capabilities",
"tags": [],
"reasons": {}
},
{
"tool": "Persona Claim by ID",
"tags": [],
"reasons": {}
},
{
"tool": "Persona ZKP Circuits",
"tags": [],
"reasons": {}
},
{
"tool": "Persona ZKP Proof by ID",
"tags": [],
"reasons": {}
},
{
"tool": "persona_context",
"tags": [],
"reasons": {}
},
{
"tool": "vault_id",
"tags": [],
"reasons": {}
},
{
"tool": "persona_preferences_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "persona_memory_digest",
"tags": [],
"reasons": {}
},
{
"tool": "query",
"tags": [],
"reasons": {}
},
{
"tool": "persona_zkp_challenge",
"tags": [],
"reasons": {}
},
{
"tool": "circuit_id",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "7123762ca4b0711b7897b901f792af718bbdf0204e25b4c1ce9a5ef89de454ac",
"stats": {
"tools": 57,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 9,
"medium": 6,
"low": 0,
"info": 0
}
}
}