Hot Memory — 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": "hot-memory-mcp",
"source": {
"kind": "package",
"origin": "hot-memory-mcp"
},
"server": {
"name": "hot-memory-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-1.13"
},
"capability": {
"level": "high",
"reasons": [
"can create, modify or delete files",
"can execute shell commands or code"
],
"tags": [
"file-write",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (56 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/memory_mcp/cli.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/memory_mcp/cli.py:209`): 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/memory_mcp/cli.py"
},
"evidence": "try: result = subprocess.run( [\"tail\", \"-200\", transcript_path], capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/memory_mcp/cli.py",
"line": 209,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/memory_mcp/project.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/memory_mcp/project.py:32`): 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/memory_mcp/project.py"
},
"evidence": "try: result = subprocess.run( [\"git\"] + args, capture_output=True, text=Tr",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/memory_mcp/project.py",
"line": 32,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-002",
"title": "Tool \"unlink_memories\" can modify the filesystem",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "Tool \"unlink_memories\" can write, overwrite or delete files (keyword \"unlink\" in tool name). Verify it is scoped to a safe directory.",
"remediation": "Constrain file operations to an explicit, non-sensitive root; reject path traversal.",
"location": {
"kind": "tool",
"name": "unlink_memories"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"unlink_memories\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"unlink_memories\" 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": "unlink_memories"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_cli.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_cli.py:229`): 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_cli.py"
},
"evidence": "nly the detached mining spawn (subprocess.run's `tail` call still delegates to the real Popen). \"\"\"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_cli.py",
"line": 229,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_hook.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_hook.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": "tests/test_hook.py"
},
"evidence": "} result = subprocess.run( [\"bash\", str(HOOK_SCRIPT)], input=json.dumps({\"transcrip",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_hook.py",
"line": 57,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_project.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_project.py:106`): 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_project.py"
},
"evidence": "a git repo subprocess.run([\"git\", \"init\"], cwd=tmpdir, capture_output=True) subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_project.py",
"line": 106,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"hot-memory-mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "hot-memory-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "remember",
"tags": [],
"reasons": {}
},
{
"tool": "recall",
"tags": [],
"reasons": {}
},
{
"tool": "recall_with_fallback",
"tags": [],
"reasons": {}
},
{
"tool": "recall_by_tag",
"tags": [],
"reasons": {}
},
{
"tool": "forget",
"tags": [],
"reasons": {}
},
{
"tool": "list_memories",
"tags": [],
"reasons": {}
},
{
"tool": "memory_stats",
"tags": [],
"reasons": {}
},
{
"tool": "preview_consolidation",
"tags": [],
"reasons": {}
},
{
"tool": "run_consolidation",
"tags": [],
"reasons": {}
},
{
"tool": "find_contradictions",
"tags": [],
"reasons": {}
},
{
"tool": "get_contradictions",
"tags": [],
"reasons": {}
},
{
"tool": "mark_contradiction",
"tags": [],
"reasons": {}
},
{
"tool": "resolve_contradiction",
"tags": [],
"reasons": {}
},
{
"tool": "hot_cache_status",
"tags": [],
"reasons": {}
},
{
"tool": "metrics_status",
"tags": [],
"reasons": {}
},
{
"tool": "promote",
"tags": [],
"reasons": {}
},
{
"tool": "demote",
"tags": [],
"reasons": {}
},
{
"tool": "pin",
"tags": [],
"reasons": {}
},
{
"tool": "unpin",
"tags": [],
"reasons": {}
},
{
"tool": "db_maintenance",
"tags": [],
"reasons": {}
},
{
"tool": "run_cleanup",
"tags": [],
"reasons": {}
},
{
"tool": "validate_embeddings",
"tags": [],
"reasons": {}
},
{
"tool": "db_info",
"tags": [],
"reasons": {}
},
{
"tool": "embedding_info",
"tags": [],
"reasons": {}
},
{
"tool": "audit_history",
"tags": [],
"reasons": {}
},
{
"tool": "db_rebuild_vectors",
"tags": [],
"reasons": {}
},
{
"tool": "log_output",
"tags": [],
"reasons": {}
},
{
"tool": "mining_status",
"tags": [],
"reasons": {}
},
{
"tool": "review_candidates",
"tags": [],
"reasons": {}
},
{
"tool": "approve_candidate",
"tags": [],
"reasons": {}
},
{
"tool": "reject_candidate",
"tags": [],
"reasons": {}
},
{
"tool": "bulk_reject_candidates",
"tags": [],
"reasons": {}
},
{
"tool": "run_mining",
"tags": [],
"reasons": {}
},
{
"tool": "access_patterns",
"tags": [],
"reasons": {}
},
{
"tool": "predict_next",
"tags": [],
"reasons": {}
},
{
"tool": "warm_cache",
"tags": [],
"reasons": {}
},
{
"tool": "predictive_cache_status",
"tags": [],
"reasons": {}
},
{
"tool": "link_memories",
"tags": [],
"reasons": {}
},
{
"tool": "unlink_memories",
"tags": [
"file-write"
],
"reasons": {
"file-write": [
"keyword \"unlink\" in tool name"
]
}
},
{
"tool": "get_related_memories",
"tags": [],
"reasons": {}
},
{
"tool": "relationship_stats",
"tags": [],
"reasons": {}
},
{
"tool": "mark_memory_used",
"tags": [],
"reasons": {}
},
{
"tool": "retrieval_quality_stats",
"tags": [],
"reasons": {}
},
{
"tool": "seed_from_text",
"tags": [],
"reasons": {}
},
{
"tool": "seed_from_file",
"tags": [],
"reasons": {}
},
{
"tool": "bootstrap_project",
"tags": [],
"reasons": {}
},
{
"tool": "get_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "get_session",
"tags": [],
"reasons": {}
},
{
"tool": "get_session_memories",
"tags": [],
"reasons": {}
},
{
"tool": "cross_session_patterns",
"tags": [],
"reasons": {}
},
{
"tool": "set_session_topic",
"tags": [],
"reasons": {}
},
{
"tool": "summarize_session",
"tags": [],
"reasons": {}
},
{
"tool": "end_session",
"tags": [],
"reasons": {}
},
{
"tool": "validate_memory",
"tags": [],
"reasons": {}
},
{
"tool": "invalidate_memory",
"tags": [],
"reasons": {}
},
{
"tool": "get_trust_history",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "9c40ad2b772ae0033a077c53f66f5f5edf25629dfd6401767fa7a439bf4bf9db",
"stats": {
"tools": 56,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 2,
"medium": 1,
"low": 4,
"info": 1
}
}
}