Basic 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": "basic-memory",
"source": {
"kind": "package",
"origin": "basic-memory"
},
"server": {
"name": "basic-memory"
}
},
"grade": "B",
"score": {
"score": 83,
"threatScore": 94,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 6.3,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"kind": "client",
"term": "capability-exposure",
"level": "critical",
"label": "capability blast radius (critical) — client exposure if the model is manipulated",
"appliedPenalty": 10
},
{
"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": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can execute shell commands or code",
"untrusted input can reach code execution"
],
"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 (18 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 (integrations/hermes/__init__.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`integrations/hermes/__init__.py:375`): 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": "integrations/hermes/__init__.py"
},
"evidence": "try: result = subprocess.run( [uv, \"tool\", \"install\", \"basic-memory\", \"--quiet\"], chec",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "integrations/hermes/__init__.py",
"line": 375,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (integrations/openclaw/commands/slash.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`integrations/openclaw/commands/slash.ts:1`): 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": "integrations/openclaw/commands/slash.ts"
},
"evidence": "{ execSync } from \"node:child_process\" import { dirname, resolve } from \"node:path\" import { fileURLToPath } from \"node:",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "integrations/openclaw/commands/slash.ts",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (integrations/openclaw/index.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`integrations/openclaw/index.ts:1`): 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": "integrations/openclaw/index.ts"
},
"evidence": "ecFileSync } from \"node:child_process\" import { definePluginEntry } from \"openclaw/plugin-sdk/plugin-entry\" import { Bm",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "integrations/openclaw/index.ts",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (integrations/openclaw/commands/slash.ts)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`integrations/openclaw/commands/slash.ts:25`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. 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": "integrations/openclaw/commands/slash.ts"
},
"evidence": "const output = execSync(`bash \"${scriptPath}\"`, { encoding: \"utf-8\", timeout: 180_000,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "integrations/openclaw/commands/slash.ts",
"line": 25,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (.agents/skills/pythonic-code/scripts/run_evals.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`.agents/skills/pythonic-code/scripts/run_evals.py:272`): 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": ".agents/skills/pythonic-code/scripts/run_evals.py"
},
"evidence": "e: result = subprocess.run( command, stdout=events_file, std",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": ".agents/skills/pythonic-code/scripts/run_evals.py",
"line": 272,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (benchmarks/scripts/read_load_bench.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/scripts/read_load_bench.py:133`): 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": "benchmarks/scripts/read_load_bench.py"
},
"evidence": "try: result = subprocess.run( command, check=True, capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "benchmarks/scripts/read_load_bench.py",
"line": 133,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (benchmarks/src/basic_memory_benchmarks/llm/runners.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/src/basic_memory_benchmarks/llm/runners.py:92`): 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": "benchmarks/src/basic_memory_benchmarks/llm/runners.py"
},
"evidence": "completed = subprocess.run( command, input=prompt,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "benchmarks/src/basic_memory_benchmarks/llm/runners.py",
"line": 92,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (benchmarks/src/basic_memory_benchmarks/utils.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/src/basic_memory_benchmarks/utils.py:35`): 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": "benchmarks/src/basic_memory_benchmarks/utils.py"
},
"evidence": "etedProcess: return subprocess.run(args, cwd=cwd, text=True, capture_output=True, check=check, env=env) def git_sh",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "benchmarks/src/basic_memory_benchmarks/utils.py",
"line": 35,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (integrations/hermes/tests/test_child_env.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`integrations/hermes/tests/test_child_env.py:160`): 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": "integrations/hermes/tests/test_child_env.py"
},
"evidence": "n. \"\"\" result = subprocess.run( [sys.executable, \"-c\", _PROBE], capture_output=True, tex",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "integrations/hermes/tests/test_child_env.py",
"line": 160,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (integrations/hermes/tests/test_integration.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`integrations/hermes/tests/test_integration.py:67`): 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": "integrations/hermes/tests/test_integration.py"
},
"evidence": "}-\") # Register subprocess.run( [_BM_BIN, \"project\", \"add\", project_name, project_dir], check=Fa",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "integrations/hermes/tests/test_integration.py",
"line": 67,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (integrations/openclaw/integration/bm-client.integration.test.ts)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`integrations/openclaw/integration/bm-client.integration.test.ts:2`): 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": "integrations/openclaw/integration/bm-client.integration.test.ts"
},
"evidence": "{ execFile } from \"node:child_process\" import { mkdir, mkdtemp, rm, stat } from \"node:fs/promises\" import { homedir, tmp",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "integrations/openclaw/integration/bm-client.integration.test.ts",
"line": 2,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "basic_memory_diagnostics",
"tags": [],
"reasons": {}
},
{
"tool": "search",
"tags": [],
"reasons": {}
},
{
"tool": "fetch",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "delete_note",
"tags": [],
"reasons": {}
},
{
"tool": "edit_note",
"tags": [],
"reasons": {}
},
{
"tool": "list_directory",
"tags": [],
"reasons": {}
},
{
"tool": "move_note",
"tags": [],
"reasons": {}
},
{
"tool": "list_memory_projects",
"tags": [],
"reasons": {}
},
{
"tool": "create_memory_project",
"tags": [],
"reasons": {}
},
{
"tool": "delete_project",
"tags": [],
"reasons": {}
},
{
"tool": "read_note",
"tags": [],
"reasons": {}
},
{
"tool": "recent_activity",
"tags": [],
"reasons": {}
},
{
"tool": "schema_validate",
"tags": [],
"reasons": {}
},
{
"tool": "schema_infer",
"tags": [],
"reasons": {}
},
{
"tool": "schema_diff",
"tags": [],
"reasons": {}
},
{
"tool": "search_notes",
"tags": [],
"reasons": {}
},
{
"tool": "view_note",
"tags": [],
"reasons": {}
},
{
"tool": "write_note",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "0e715d5c6660fba89787ba101a90c580a2ed4be6434057294deb4ec0dbfccd7c",
"stats": {
"tools": 18,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 3,
"medium": 1,
"low": 7,
"info": 0
}
}
}