Obsidian — 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": "@mseep/obsidian-mcp-server",
"source": {
"kind": "package",
"origin": "@mseep/obsidian-mcp-server"
},
"server": {
"name": "@mseep/obsidian-mcp-server"
}
},
"grade": "A",
"score": {
"score": 92,
"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": "none",
"label": "publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read",
"appliedPenalty": 2
},
{
"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 create, modify or delete files",
"can execute shell commands or code"
],
"tags": [
"file-write",
"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-002",
"title": "Shell/command execution in server code (obsidian-ai-curator-plugin/src/claude-cli-wrapper.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`obsidian-ai-curator-plugin/src/claude-cli-wrapper.ts: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": "obsidian-ai-curator-plugin/src/claude-cli-wrapper.ts"
},
"evidence": "import { spawn } from 'child_process'; import { EventEmitter } from 'events'; export interface ClaudeCliOptions { mo",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "obsidian-ai-curator-plugin/src/claude-cli-wrapper.ts",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (obsidian-ai-curator-plugin/src/git-service.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`obsidian-ai-curator-plugin/src/git-service.ts: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": "obsidian-ai-curator-plugin/src/git-service.ts"
},
"evidence": "import { spawn } from 'child_process'; import { App } from 'obsidian'; export class GitService { private vaultPath:",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "obsidian-ai-curator-plugin/src/git-service.ts",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/tools/claude-code-executor.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/tools/claude-code-executor.js:6`): 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/tools/claude-code-executor.js"
},
"evidence": "t { exec, spawn } from 'child_process'; import { promisify } from 'util'; import fs from 'fs/promises'; import path from",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/tools/claude-code-executor.js",
"line": 6,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/tools/github/github-integration.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/tools/github/github-integration.js:6`): 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/tools/github/github-integration.js"
},
"evidence": "import { exec } from 'child_process'; import { promisify } from 'util'; import fs from 'fs/promises'; import path from",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/tools/github/github-integration.js",
"line": 6,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-002",
"title": "Tool \"move_file\" can modify the filesystem",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "Tool \"move_file\" can write, overwrite or delete files (keyword \"move_file\" in tool name). Verify it is scoped to a safe directory.",
"remediation": "Constrain file operations to an explicit, non-sensitive root; reject path traversal.",
"location": {
"kind": "tool",
"name": "move_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"move_file\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"move_file\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "move_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/test-claude-headless.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/test-claude-headless.js:42`): 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": "scripts/test-claude-headless.js"
},
"evidence": "exec } = await import('child_process'); const { promisify } = await import('util'); const execAsync = promisify",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/test-claude-headless.js",
"line": 42,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/test-github-integration.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/test-github-integration.js:9`): 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": "scripts/test-github-integration.js"
},
"evidence": "; import { exec } from 'child_process'; import { promisify } from 'util'; const execAsync = promisify(exec); // Colors",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/test-github-integration.js",
"line": 9,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/test-local-claude.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/test-local-claude.js:9`): 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": "scripts/test-local-claude.js"
},
"evidence": "; import { exec } from 'child_process'; import { promisify } from 'util'; const execAsync = promisify(exec); // Colors",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/test-local-claude.js",
"line": 9,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (test/run-tests.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`test/run-tests.js:3`): 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": "test/run-tests.js"
},
"evidence": "import { spawn } from 'child_process'; import { fileURLToPath } from 'url'; import path from 'path'; import fs from 'fs",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "test/run-tests.js",
"line": 3,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (test/test-status.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`test/test-status.js:3`): 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": "test/test-status.js"
},
"evidence": "port { execSync } from 'child_process'; console.log(` ╔════════════════════════════════════════════════════════════════",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "test/test-status.js",
"line": 3,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"@mseep/obsidian-mcp-server\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
"remediation": "Prefer packages that link to public, reviewable source.",
"location": {
"kind": "package",
"name": "@mseep/obsidian-mcp-server"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "vault_scan",
"tags": [],
"reasons": {}
},
{
"tool": "read_notes",
"tags": [],
"reasons": {}
},
{
"tool": "write_note",
"tags": [],
"reasons": {}
},
{
"tool": "search_content",
"tags": [],
"reasons": {}
},
{
"tool": "get_tags",
"tags": [],
"reasons": {}
},
{
"tool": "init_project",
"tags": [],
"reasons": {}
},
{
"tool": "list_playbooks",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_tags",
"tags": [],
"reasons": {}
},
{
"tool": "suggest_tags",
"tags": [],
"reasons": {}
},
{
"tool": "update_tags",
"tags": [],
"reasons": {}
},
{
"tool": "get_tag_taxonomy",
"tags": [],
"reasons": {}
},
{
"tool": "validate_tags",
"tags": [],
"reasons": {}
},
{
"tool": "get_daily_note",
"tags": [],
"reasons": {}
},
{
"tool": "append_to_daily_note",
"tags": [],
"reasons": {}
},
{
"tool": "rename_file",
"tags": [],
"reasons": {}
},
{
"tool": "move_file",
"tags": [
"file-write"
],
"reasons": {
"file-write": [
"keyword \"move_file\" in tool name"
]
}
},
{
"tool": "create_github_issue",
"tags": [],
"reasons": {}
},
{
"tool": "create_bug_report",
"tags": [],
"reasons": {}
},
{
"tool": "create_feature_request",
"tags": [],
"reasons": {}
},
{
"tool": "check_issue_status",
"tags": [],
"reasons": {}
},
{
"tool": "execute_claude_code_fix",
"tags": [],
"reasons": {}
},
{
"tool": "execute_claude_code_feature",
"tags": [],
"reasons": {}
},
{
"tool": "check_claude_code_status",
"tags": [],
"reasons": {}
},
{
"tool": "cleanup_temp_directories",
"tags": [],
"reasons": {}
},
{
"tool": "git_checkpoint",
"tags": [],
"reasons": {}
},
{
"tool": "git_changes",
"tags": [],
"reasons": {}
},
{
"tool": "git_rollback",
"tags": [],
"reasons": {}
},
{
"tool": "find_by_metadata",
"tags": [],
"reasons": {}
},
{
"tool": "add_daily_task",
"tags": [],
"reasons": {}
},
{
"tool": "update_frontmatter",
"tags": [],
"reasons": {}
},
{
"tool": "list_project_templates",
"tags": [],
"reasons": {}
},
{
"tool": "archive_notes",
"tags": [],
"reasons": {}
},
{
"tool": "document_design_decision",
"tags": [],
"reasons": {}
},
{
"tool": "view_performance_metrics",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "26d8109deb7839c89749903becf066b905ebe17d18bd5dc4a2e87cb35c724983",
"stats": {
"tools": 34,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 1,
"low": 6,
"info": 1
}
}
}