Engram Mem — 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": "engram-mem",
"source": {
"kind": "package",
"origin": "engram-mem"
},
"server": {
"name": "engram-mem"
}
},
"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 (21 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/engram/cli/autostart_cmd.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/engram/cli/autostart_cmd.py:89`): 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/engram/cli/autostart_cmd.py"
},
"evidence": "# Reload systemd subprocess.run([\"systemctl\", \"--user\", \"daemon-reload\"], check=True) # Enable and start",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/engram/cli/autostart_cmd.py",
"line": 89,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/engram/cli/daemon_cmd.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/engram/cli/daemon_cmd.py:154`): 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/engram/cli/daemon_cmd.py"
},
"evidence": "subprocess subprocess.run([\"tail\", \"-n\", str(lines), str(_LOG_FILE)])",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/engram/cli/daemon_cmd.py",
"line": 154,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/engram/cli/init_cmd.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/engram/cli/init_cmd.py:278`): 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/engram/cli/init_cmd.py"
},
"evidence": "try: result = subprocess.run( [engram_bin, \"start\"], capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/engram/cli/init_cmd.py",
"line": 278,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/engram/health/components.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/engram/health/components.py:147`): 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/engram/health/components.py"
},
"evidence": "try: result = subprocess.run( [\"pgrep\", \"-f\", \"engram watch\"], capture_output=True, text=True, tim",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/engram/health/components.py",
"line": 147,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/engram/setup/connectors/aider.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/engram/setup/connectors/aider.py:142`): 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/engram/setup/connectors/aider.py"
},
"evidence": "try: result = subprocess.run( [binary, \"--version\"], capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/engram/setup/connectors/aider.py",
"line": 142,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/engram/setup/connectors/claude_code.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/engram/setup/connectors/claude_code.py:148`): 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/engram/setup/connectors/claude_code.py"
},
"evidence": "try: result = subprocess.run( [binary, \"--version\"], capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/engram/setup/connectors/claude_code.py",
"line": 148,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/engram/setup/connectors/cursor.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/engram/setup/connectors/cursor.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": "src/engram/setup/connectors/cursor.py"
},
"evidence": "try: result = subprocess.run( [binary, \"--version\"], capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/engram/setup/connectors/cursor.py",
"line": 56,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/engram/setup/connectors/github_copilot.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/engram/setup/connectors/github_copilot.py:76`): 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/engram/setup/connectors/github_copilot.py"
},
"evidence": "y: result = subprocess.run( [binary, \"--list-extensions\"], capture_output=Tr",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/engram/setup/connectors/github_copilot.py",
"line": 76,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/engram/setup/connectors/openclaw.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/engram/setup/connectors/openclaw.py:168`): 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/engram/setup/connectors/openclaw.py"
},
"evidence": "try: result = subprocess.run( [binary, \"--version\"], capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/engram/setup/connectors/openclaw.py",
"line": 168,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/engram/setup/connectors/void_editor.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/engram/setup/connectors/void_editor.py:57`): 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/engram/setup/connectors/void_editor.py"
},
"evidence": "try: result = subprocess.run( [binary, \"--version\"], capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/engram/setup/connectors/void_editor.py",
"line": 57,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "engram_remember",
"tags": [],
"reasons": {}
},
{
"tool": "engram_recall",
"tags": [],
"reasons": {}
},
{
"tool": "engram_get_memory",
"tags": [],
"reasons": {}
},
{
"tool": "engram_timeline",
"tags": [],
"reasons": {}
},
{
"tool": "engram_cleanup",
"tags": [],
"reasons": {}
},
{
"tool": "engram_cleanup_dedup",
"tags": [],
"reasons": {}
},
{
"tool": "engram_meeting_ledger",
"tags": [],
"reasons": {}
},
{
"tool": "engram_ingest",
"tags": [],
"reasons": {}
},
{
"tool": "engram_feedback",
"tags": [],
"reasons": {}
},
{
"tool": "engram_auto_feedback",
"tags": [],
"reasons": {}
},
{
"tool": "engram_ask",
"tags": [],
"reasons": {}
},
{
"tool": "engram_think",
"tags": [],
"reasons": {}
},
{
"tool": "engram_summarize",
"tags": [],
"reasons": {}
},
{
"tool": "engram_status",
"tags": [],
"reasons": {}
},
{
"tool": "engram_add_entity",
"tags": [],
"reasons": {}
},
{
"tool": "engram_add_relation",
"tags": [],
"reasons": {}
},
{
"tool": "engram_query_graph",
"tags": [],
"reasons": {}
},
{
"tool": "engram_session_start",
"tags": [],
"reasons": {}
},
{
"tool": "engram_session_end",
"tags": [],
"reasons": {}
},
{
"tool": "engram_session_summary",
"tags": [],
"reasons": {}
},
{
"tool": "engram_session_context",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "d88e96311c617ca46e52690e7620b176db5846b351d0d4a53ee5e8846245947a",
"stats": {
"tools": 21,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 10,
"medium": 0,
"low": 0,
"info": 0
}
}
}