Cerebro Code Memory — 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": "cerebro-code-memory",
"source": {
"kind": "package",
"origin": "cerebro-code-memory"
},
"server": {
"name": "cerebro-code-memory"
}
},
"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": [
"can execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (16 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 (plugin/hooks/cerebro-session-end.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`plugin/hooks/cerebro-session-end.py:107`): 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": "plugin/hooks/cerebro-session-end.py"
},
"evidence": "try: subprocess.Popen( cmd, env=env, stdout=subprocess.DEVNULL, stder",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "plugin/hooks/cerebro-session-end.py",
"line": 107,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (plugin/hooks/post_edit.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`plugin/hooks/post_edit.py:43`): 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": "plugin/hooks/post_edit.py"
},
"evidence": "ndex\"] try: subprocess.run(base + [fpath], env=env, capture_output=True, text=True, timeout=30) except E",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "plugin/hooks/post_edit.py",
"line": 43,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (plugin/hooks/session_start.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`plugin/hooks/session_start.py: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": "plugin/hooks/session_start.py"
},
"evidence": ") try: subprocess.run(graph_cmd, env=env, capture_output=True, text=True, timeout=30) except Except",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "plugin/hooks/session_start.py",
"line": 56,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (plugin/hooks/verify-edit.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`plugin/hooks/verify-edit.py:54`): 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": "plugin/hooks/verify-edit.py"
},
"evidence": "th try: p = subprocess.run([exe] + cmd[1:], cwd=cwd, capture_output=True, text=Tr",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "plugin/hooks/verify-edit.py",
"line": 54,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/cerebro/config.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/cerebro/config.py:77`): 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/cerebro/config.py"
},
"evidence": "try: out = subprocess.run( [\"git\", \"-C\", str(start_path), \"rev-parse\", \"--show-toplevel\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/cerebro/config.py",
"line": 77,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/cerebro/gitsync.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/cerebro/gitsync.py:20`): 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/cerebro/gitsync.py"
},
"evidence": "try: out = subprocess.run( [\"git\", \"-C\", str(repo_abs), *args], capture_output=True",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/cerebro/gitsync.py",
"line": 20,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/cerebro/summarizer.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/cerebro/summarizer.py:64`): 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/cerebro/summarizer.py"
},
"evidence": "try: out = subprocess.run( [_claude_bin(), \"-p\", \"--model\", model], input=prompt,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/cerebro/summarizer.py",
"line": 64,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_gitsync.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_gitsync.py:7`): 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": "tests/test_gitsync.py"
},
"evidence": "f git(root, *args): subprocess.run([\"git\", \"-C\", str(root), *args], capture_output=True, check=True) def write(roo",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_gitsync.py",
"line": 7,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "cerebro_map",
"tags": [],
"reasons": {}
},
{
"tool": "cerebro_get",
"tags": [],
"reasons": {}
},
{
"tool": "cerebro_search",
"tags": [],
"reasons": {}
},
{
"tool": "cerebro_record",
"tags": [],
"reasons": {}
},
{
"tool": "cerebro_stale",
"tags": [],
"reasons": {}
},
{
"tool": "cerebro_sync",
"tags": [],
"reasons": {}
},
{
"tool": "cerebro_reindex",
"tags": [],
"reasons": {}
},
{
"tool": "cerebro_note",
"tags": [],
"reasons": {}
},
{
"tool": "cerebro_recall",
"tags": [],
"reasons": {}
},
{
"tool": "cerebro_impact",
"tags": [],
"reasons": {}
},
{
"tool": "cerebro_cycles",
"tags": [],
"reasons": {}
},
{
"tool": "cerebro_callers",
"tags": [],
"reasons": {}
},
{
"tool": "cerebro_calls",
"tags": [],
"reasons": {}
},
{
"tool": "cerebro_orphans",
"tags": [],
"reasons": {}
},
{
"tool": "cerebro_dead_symbols",
"tags": [],
"reasons": {}
},
{
"tool": "cerebro_endpoints",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "9dd26544a11ace7125e69eb0be38a421d5c279207de4e0356a9392cfd7bfa438",
"stats": {
"tools": 16,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 7,
"medium": 0,
"low": 1,
"info": 0
}
}
}