Engram — 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": "mcp-engram",
"source": {
"kind": "package",
"origin": "mcp-engram"
},
"server": {
"name": "mcp-engram"
}
},
"grade": "B",
"score": {
"score": 87,
"threatScore": 94,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 6.3,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"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-1.13"
},
"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 (26 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-CAP-001",
"title": "Tool \"spawn_subtask\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"spawn_subtask\" appears to run shell commands or evaluate code (keyword \"spawn\" in tool name). 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": "spawn_subtask"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/engram/daemon.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/engram/daemon.py:40`): 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/daemon.py"
},
"evidence": "try: out = subprocess.check_output( [\"ps\", \"-p\", str(pid), \"-o\", \"command=\"], text=True, timeou",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/engram/daemon.py",
"line": 40,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/engram/runtime/injector.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/engram/runtime/injector.py:69`): 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/runtime/injector.py"
},
"evidence": "try: out = subprocess.run( [git_path, *args], cwd=cwd, capture_output=T",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/engram/runtime/injector.py",
"line": 69,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/engram/shared.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/engram/shared.py:103`): 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/shared.py"
},
"evidence": "y: result = subprocess.run( cmd, capture_output=True, text=T",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/engram/shared.py",
"line": 103,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (src/engram/graph.py)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/engram/graph.py:63`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). 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/graph.py"
},
"evidence": "g = pickle.load(f) self._dirty = True # Mark pkl for deletion — will",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "src/engram/graph.py",
"line": 63,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"spawn_subtask\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"spawn_subtask\" 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": "spawn_subtask"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (benchmark/locomo_eval.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`benchmark/locomo_eval.py:237`): 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": "benchmark/locomo_eval.py"
},
"evidence": "import subprocess subprocess.run([\"curl\", \"-sL\", \"-o\", str(path), DATA_URL], check=True) print(f\" saved to {p",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "benchmark/locomo_eval.py",
"line": 237,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_lock_conflict.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_lock_conflict.py:101`): 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_lock_conflict.py"
},
"evidence": "h / \".ready\" proc = subprocess.Popen( [sys.executable, \"-c\", _HOLDER_SCRIPT, str(db_path), str(ready_path)],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_lock_conflict.py",
"line": 101,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"mcp-engram\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "mcp-engram"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "recall_memory",
"tags": [],
"reasons": {}
},
{
"tool": "store_memory",
"tags": [],
"reasons": {}
},
{
"tool": "update_memory",
"tags": [],
"reasons": {}
},
{
"tool": "consolidate_memory",
"tags": [],
"reasons": {}
},
{
"tool": "session_handoff",
"tags": [],
"reasons": {}
},
{
"tool": "memory_stats",
"tags": [],
"reasons": {}
},
{
"tool": "track_failure",
"tags": [],
"reasons": {}
},
{
"tool": "track_progress",
"tags": [],
"reasons": {}
},
{
"tool": "session_outcome",
"tags": [],
"reasons": {}
},
{
"tool": "create_task",
"tags": [],
"reasons": {}
},
{
"tool": "update_task",
"tags": [],
"reasons": {}
},
{
"tool": "get_task",
"tags": [],
"reasons": {}
},
{
"tool": "list_tasks",
"tags": [],
"reasons": {}
},
{
"tool": "restore_checkpoint",
"tags": [],
"reasons": {}
},
{
"tool": "list_checkpoints",
"tags": [],
"reasons": {}
},
{
"tool": "get_runtime_health",
"tags": [],
"reasons": {}
},
{
"tool": "report_interruption",
"tags": [],
"reasons": {}
},
{
"tool": "evaluate_continuity",
"tags": [],
"reasons": {}
},
{
"tool": "start_execution",
"tags": [],
"reasons": {}
},
{
"tool": "retry_task",
"tags": [],
"reasons": {}
},
{
"tool": "spawn_subtask",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"spawn\" in tool name"
]
}
},
{
"tool": "trace_execution",
"tags": [],
"reasons": {}
},
{
"tool": "end_execution",
"tags": [],
"reasons": {}
},
{
"tool": "detect_drift",
"tags": [],
"reasons": {}
},
{
"tool": "score_recovery",
"tags": [],
"reasons": {}
},
{
"tool": "recommend_recovery",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "9722b3993c5f733237239cb8089f05aa2c74429c6de90cb47dd7a63f83d8e8d5",
"stats": {
"tools": 26,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 1,
"low": 3,
"info": 1
}
}
}