Tokesave — 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": "tokesave-mcp",
"source": {
"kind": "package",
"origin": "tokesave-mcp"
},
"server": {
"name": "tokesave-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": [
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"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 (28 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 (src/proxy.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/proxy.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": "src/proxy.js"
},
"evidence": "st { spawn } = require('child_process'); const { Transform } = require('stream'); const compressor = require('./compress",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/proxy.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/repo_audit.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/repo_audit.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": "src/repo_audit.js"
},
"evidence": "{ execSync } = require('child_process'); const fs = require('fs'); const path = require('path'); const BINARY_EXTS = ne",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/repo_audit.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/repo_cleanup.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/repo_cleanup.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": "src/repo_cleanup.js"
},
"evidence": "spawnSync } = require('child_process'); const fs = require('fs'); const path = require('path'); const COMMON_GITIGNORE",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/repo_cleanup.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"filePath\" on \"read_file_range\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"read_file_range\" takes a path parameter \"filePath\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "read_file_range",
"field": "inputSchema.properties.filePath"
},
"data": {
"param": "filePath"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "TokeSave System Prompt",
"tags": [],
"reasons": {}
},
{
"tool": "auto_setup",
"tags": [],
"reasons": {}
},
{
"tool": "compress_text",
"tags": [],
"reasons": {}
},
{
"tool": "compress_file",
"tags": [],
"reasons": {}
},
{
"tool": "compress_batch",
"tags": [],
"reasons": {}
},
{
"tool": "summarize_file",
"tags": [],
"reasons": {}
},
{
"tool": "read_function_body",
"tags": [],
"reasons": {}
},
{
"tool": "diff_files",
"tags": [],
"reasons": {}
},
{
"tool": "compress_url",
"tags": [],
"reasons": {}
},
{
"tool": "compress_file_chunked",
"tags": [],
"reasons": {}
},
{
"tool": "recall_memory",
"tags": [],
"reasons": {}
},
{
"tool": "scan_injection",
"tags": [],
"reasons": {}
},
{
"tool": "set_mode",
"tags": [],
"reasons": {}
},
{
"tool": "get_stats",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"get_token\""
]
}
},
{
"tool": "get_status",
"tags": [],
"reasons": {}
},
{
"tool": "swarm_create_agent",
"tags": [],
"reasons": {}
},
{
"tool": "swarm_assign_task",
"tags": [],
"reasons": {}
},
{
"tool": "swarm_get_status",
"tags": [],
"reasons": {}
},
{
"tool": "benchmark",
"tags": [],
"reasons": {}
},
{
"tool": "repo_audit",
"tags": [],
"reasons": {}
},
{
"tool": "repo_cleanup",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"list_files\""
]
}
},
{
"tool": "repo_cleanup_apply",
"tags": [],
"reasons": {}
},
{
"tool": "grep_files",
"tags": [],
"reasons": {}
},
{
"tool": "read_file_range",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"read_file\""
]
}
},
{
"tool": "file_mtree",
"tags": [],
"reasons": {}
},
{
"tool": "generate_proxy_config",
"tags": [],
"reasons": {}
},
{
"tool": "check_context_pressure",
"tags": [],
"reasons": {}
},
{
"tool": "compress_output",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "b69af0528848e8bc14173acb8d6a631fa8b47a452f27d8c30dd0648e035ebbb3",
"stats": {
"tools": 28,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 3,
"medium": 0,
"low": 1,
"info": 0
}
}
}