Synapse Orch Ai — 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": "synapse-orch-ai",
"source": {
"kind": "package",
"origin": "synapse-orch-ai"
},
"server": {
"name": "synapse-orch-ai"
}
},
"grade": "B",
"score": {
"score": 83,
"threatScore": 94,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 6.3,
"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": "client",
"term": "capability-exposure",
"level": "critical",
"label": "capability blast radius (critical) — client exposure if the model is manipulated",
"appliedPenalty": 10
},
{
"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": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code",
"untrusted-input, sensitive-source and egress co-exist across tools (toxic-flow surface)",
"untrusted input can reach code execution"
],
"tags": [
"code-exec",
"sensitive-source",
"untrusted-input"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (33 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-002",
"title": "Completed toxic-flow trifecta across tools",
"category": "exfiltration",
"severity": "critical",
"confidence": "strong",
"description": "This server (without client built-ins) exposes a complete data-exfiltration chain: crawl_multiple → read_file_by_lines → run_bash. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.",
"remediation": "Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.",
"location": {
"kind": "flow",
"name": "crawl_multiple → read_file_by_lines → run_bash"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"untrusted": [
"scrape_url",
"scrape_structured",
"crawl_multiple",
"scrape_with_session"
],
"sources": [
"read_file_by_lines",
"vault_write",
"vault_patch",
"vault_list",
"run_sql_query"
],
"sinks": [
"run_bash"
],
"path": [
"crawl_multiple",
"read_file_by_lines",
"run_bash"
],
"edges": [
{
"from": "crawl_multiple",
"to": "read_file_by_lines",
"kind": "agent-mediated"
},
{
"from": "read_file_by_lines",
"to": "run_bash",
"kind": "agent-mediated"
}
],
"wired": false
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"run_bash\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"run_bash\" appears to run shell commands or evaluate code (keyword \"bash\" in tool name, parameter \"command\"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "run_bash"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (backend/core/orchestration/steps.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`backend/core/orchestration/steps.py:1680`): 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": "backend/core/orchestration/steps.py"
},
"evidence": "result = bool(eval(condition, eval_ns)) except Exception as e: print(f\"DEBUG IF_ELSE: ⚠ Co",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "backend/core/orchestration/steps.py",
"line": 1680,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (backend/tools/bash.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`backend/tools/bash.py:193`): 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": "backend/tools/bash.py"
},
"evidence": "try: result = subprocess.run( shell_cmd, cwd=cwd, capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "backend/tools/bash.py",
"line": 193,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (bin/synapse.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/synapse.js:4`): 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": "bin/synapse.js"
},
"evidence": "ync, spawn } = require('child_process'); const path = require('path'); const fs = require('fs'); const crypto = require(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/synapse.js",
"line": 4,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (bin/synapse.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`bin/synapse.js:45`): 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": "bin/synapse.js"
},
"evidence": "t result = IS_WIN ? spawnSync(`${cmd} --version`, { stdio: 'pipe', shell: true }) : spawnSync(cmd, ['--version']",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "bin/synapse.js",
"line": 45,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url\" on \"scrape_url\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"scrape_url\" takes a URL/host parameter \"url\" 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": "scrape_url",
"field": "inputSchema.properties.url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url"
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url\" on \"scrape_with_session\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"scrape_with_session\" takes a URL/host parameter \"url\" 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": "scrape_with_session",
"field": "inputSchema.properties.url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"command\" on \"run_bash\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"run_bash\" takes a command-shaped parameter \"command\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
"remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
"location": {
"kind": "tool",
"name": "run_bash",
"field": "inputSchema.properties.command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "command"
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (frontend-build/.next/server/chunks/[turbopack]_runtime.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`frontend-build/.next/server/chunks/[turbopack]_runtime.js:601`): 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": "frontend-build/.next/server/chunks/[turbopack]_runtime.js"
},
"evidence": "y { raw = await import(id); } catch (err) { // TODO(alexkirsz) This can happen when a client-side mo",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "frontend-build/.next/server/chunks/[turbopack]_runtime.js",
"line": 601,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (frontend-build/.next/server/chunks/ssr/[turbopack]_runtime.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`frontend-build/.next/server/chunks/ssr/[turbopack]_runtime.js:601`): 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": "frontend-build/.next/server/chunks/ssr/[turbopack]_runtime.js"
},
"evidence": "y { raw = await import(id); } catch (err) { // TODO(alexkirsz) This can happen when a client-side mo",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "frontend-build/.next/server/chunks/ssr/[turbopack]_runtime.js",
"line": 601,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"run_bash\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"run_bash\" 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": "run_bash"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"file_path\" on \"read_file_by_lines\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"read_file_by_lines\" takes a path parameter \"file_path\" 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_by_lines",
"field": "inputSchema.properties.file_path"
},
"data": {
"param": "file_path"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"path\" on \"vault_write\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"vault_write\" takes a path parameter \"path\" 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": "vault_write",
"field": "inputSchema.properties.path"
},
"data": {
"param": "path"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"path\" on \"vault_patch\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"vault_patch\" takes a path parameter \"path\" 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": "vault_patch",
"field": "inputSchema.properties.path"
},
"data": {
"param": "path"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"directory\" on \"vault_list\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"vault_list\" takes a path parameter \"directory\" 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": "vault_list",
"field": "inputSchema.properties.directory"
},
"data": {
"param": "directory"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "critical",
"confidence": "strong",
"untrustedInput": [
"scrape_url",
"scrape_structured",
"crawl_multiple",
"scrape_with_session"
],
"sensitiveSource": [
"read_file_by_lines",
"vault_write",
"vault_patch",
"vault_list",
"run_sql_query"
],
"externalSink": [
"run_bash"
],
"selfContained": false,
"path": [
"crawl_multiple",
"read_file_by_lines",
"run_bash"
],
"pathWired": false,
"description": "A cross-tool exfiltration chain exists: crawl_multiple → read_file_by_lines → run_bash."
}
],
"capabilities": [
{
"tool": "run_bash",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"bash\" in tool name",
"parameter \"command\""
]
}
},
{
"tool": "search_codebase",
"tags": [],
"reasons": {}
},
{
"tool": "multi_repo_search",
"tags": [],
"reasons": {}
},
{
"tool": "find_similar_code",
"tags": [],
"reasons": {}
},
{
"tool": "list_indexed_files",
"tags": [],
"reasons": {}
},
{
"tool": "get_file_chunks",
"tags": [],
"reasons": {}
},
{
"tool": "grep",
"tags": [],
"reasons": {}
},
{
"tool": "glob",
"tags": [],
"reasons": {}
},
{
"tool": "read_file_by_lines",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"read_file\""
]
}
},
{
"tool": "collect_data",
"tags": [],
"reasons": {}
},
{
"tool": "grep_file",
"tags": [],
"reasons": {}
},
{
"tool": "parse_pdf",
"tags": [],
"reasons": {}
},
{
"tool": "get_personal_details",
"tags": [],
"reasons": {}
},
{
"tool": "vault_create",
"tags": [],
"reasons": {}
},
{
"tool": "vault_read",
"tags": [],
"reasons": {}
},
{
"tool": "vault_write",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"list_files\""
]
}
},
{
"tool": "vault_patch",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"list_files\""
]
}
},
{
"tool": "vault_list",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"list_files\""
]
}
},
{
"tool": "vault_delete",
"tags": [],
"reasons": {}
},
{
"tool": "execute_python",
"tags": [],
"reasons": {}
},
{
"tool": "tool_code",
"tags": [],
"reasons": {}
},
{
"tool": "list_tables",
"tags": [],
"reasons": {}
},
{
"tool": "get_table_schema",
"tags": [],
"reasons": {}
},
{
"tool": "run_sql_query",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"run_sql\""
]
}
},
{
"tool": "get_datetime",
"tags": [],
"reasons": {}
},
{
"tool": "scrape_url",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"scrape\""
]
}
},
{
"tool": "scrape_structured",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"scrape\""
]
}
},
{
"tool": "crawl_multiple",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"crawl\""
]
}
},
{
"tool": "extract_links",
"tags": [],
"reasons": {}
},
{
"tool": "screenshot_url",
"tags": [],
"reasons": {}
},
{
"tool": "scrape_with_session",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"scrape\""
]
}
},
{
"tool": "search_page",
"tags": [],
"reasons": {}
},
{
"tool": "parse_xlsx",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "b6557a9331d500f322a1efd7a0a849f95a1dab61657235fabf212528f2acb74b",
"stats": {
"tools": 33,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 1,
"high": 4,
"medium": 6,
"low": 5,
"info": 0
}
}
}