Brainstem — 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": "brainstem-mcp",
"source": {
"kind": "package",
"origin": "brainstem-mcp"
},
"server": {
"name": "brainstem-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-1.9"
},
"capability": {
"level": "high",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can execute shell commands or code"
],
"tags": [
"untrusted-input",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (27 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/wiki_agent/doctor.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/wiki_agent/doctor.py:151`): 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/wiki_agent/doctor.py"
},
"evidence": "rm.system()}\") rc = os.system(\"systemctl --user is-active wiki-ingest.service >/dev/null 2>&1\") >> 8 # noqa: S605",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/wiki_agent/doctor.py",
"line": 151,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/wiki_papers/extract.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/wiki_papers/extract.py:117`): 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/wiki_papers/extract.py"
},
"evidence": "try: proc = subprocess.run( [\"java\", \"-version\"], capture_output=True, text=True, timeout=15, ch",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/wiki_papers/extract.py",
"line": 117,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/wiki_publishing/project_context_source.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/wiki_publishing/project_context_source.py:137`): 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/wiki_publishing/project_context_source.py"
},
"evidence": "gs) completed = subprocess.run( # noqa: S603 — fixed argv, no shell, guarded args [\"git\", \"-C\", str",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/wiki_publishing/project_context_source.py",
"line": 137,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/wiki_repos/cbm_runner.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/wiki_repos/cbm_runner.py:55`): 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/wiki_repos/cbm_runner.py"
},
"evidence": "ut).\"\"\" completed = subprocess.run( # noqa: S603 cmd, timeout=timeout, capture_output=True, text=True, chec",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/wiki_repos/cbm_runner.py",
"line": 55,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/wiki_repos/codegraph_runner.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/wiki_repos/codegraph_runner.py:58`): 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/wiki_repos/codegraph_runner.py"
},
"evidence": "\"\"\" completed = subprocess.run(cmd, timeout=timeout, check=False) # noqa: S603 return completed.returncode",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/wiki_repos/codegraph_runner.py",
"line": 58,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/wiki_repos/render.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/wiki_repos/render.py:75`): 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/wiki_repos/render.py"
},
"evidence": "oat) -> int: return subprocess.run( # noqa: S603 — fixed argv, no shell cmd, env=env, timeout=timeout, capt",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/wiki_repos/render.py",
"line": 75,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "search_wiki_index",
"tags": [],
"reasons": {}
},
{
"tool": "read_wiki_file",
"tags": [],
"reasons": {}
},
{
"tool": "get_wiki_stats",
"tags": [],
"reasons": {}
},
{
"tool": "find_cross_references",
"tags": [],
"reasons": {}
},
{
"tool": "detect_orphan_pages",
"tags": [],
"reasons": {}
},
{
"tool": "validate_frontmatter",
"tags": [],
"reasons": {}
},
{
"tool": "code_graph_overview",
"tags": [],
"reasons": {}
},
{
"tool": "ask_repo",
"tags": [],
"reasons": {}
},
{
"tool": "code_graph_contexts",
"tags": [],
"reasons": {}
},
{
"tool": "code_graph_subgraph",
"tags": [],
"reasons": {}
},
{
"tool": "code_graph_impact",
"tags": [],
"reasons": {}
},
{
"tool": "write_page",
"tags": [],
"reasons": {}
},
{
"tool": "update_index_entry",
"tags": [],
"reasons": {}
},
{
"tool": "append_to_log",
"tags": [],
"reasons": {}
},
{
"tool": "web_clip",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "update_schema_lessons",
"tags": [],
"reasons": {}
},
{
"tool": "ingest_github_repo",
"tags": [],
"reasons": {}
},
{
"tool": "ingest_arxiv_paper",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "linkedin_draft_from_wiki",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_draft_from_repo",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_draft_from_url",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_draft_project_post",
"tags": [],
"reasons": {}
},
{
"tool": "linkedin_publish_draft",
"tags": [],
"reasons": {}
},
{
"tool": "memory_tree_recall",
"tags": [],
"reasons": {}
},
{
"tool": "memory_tree_seal_now",
"tags": [],
"reasons": {}
},
{
"tool": "memory_tree_list_topics",
"tags": [],
"reasons": {}
},
{
"tool": "memory_tree_tombstone",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "791f54fe681664b11cb3141736fd8d878c75dc0447f2772feb317f9184a5de38",
"stats": {
"tools": 27,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 6,
"medium": 0,
"low": 0,
"info": 0
}
}
}