Tenets — 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": "tenets",
"source": {
"kind": "package",
"origin": "tenets"
},
"server": {
"name": "tenets"
}
},
"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": [
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"sensitive-source",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (10 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-006",
"title": "Reads a sensitive credential path or dumps the environment (tenets/core/analysis/analyzer.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tenets/core/analysis/analyzer.py:566`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. 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": "tenets/core/analysis/analyzer.py"
},
"evidence": "torconfig\", \".npmrc\", \".yarnrc\", \".nvmrc\", } if file_path.name in sp",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "tenets/core/analysis/analyzer.py",
"line": 566,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (tenets/cli/app.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tenets/cli/app.py:36`): 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": "tenets/cli/app.py"
},
"evidence": "ocess result = subprocess.run( [\"git\", \"--version\"], check=False, capture_output=True, text=True, t",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tenets/cli/app.py",
"line": 36,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (tenets/cli/commands/distill.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tenets/cli/commands/distill.py:508`): 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": "tenets/cli/commands/distill.py"
},
"evidence": "subprocess.run([\"open\", folder], check=False) else: # Linux",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tenets/cli/commands/distill.py",
"line": 508,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (tenets/cli/commands/rank.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tenets/cli/commands/rank.py:366`): 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": "tenets/cli/commands/rank.py"
},
"evidence": "subprocess.run([\"open\", folder], check=False) else: # Linux",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tenets/cli/commands/rank.py",
"line": 366,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (tenets/cli/commands/system_instruction.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tenets/cli/commands/system_instruction.py:438`): 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": "tenets/cli/commands/system_instruction.py"
},
"evidence": "Open editor subprocess.call([editor, tmp_path]) # Read edited content with open(tmp",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tenets/cli/commands/system_instruction.py",
"line": 438,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (tenets/core/git/analyzer.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tenets/core/git/analyzer.py:399`): 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": "tenets/core/git/analyzer.py"
},
"evidence": "result = subprocess.run( cmd, cwd=str(self.root), capture_output=True, text=True, tim",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tenets/core/git/analyzer.py",
"line": 399,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (tenets/core/git/blame.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tenets/core/git/blame.py:399`): 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": "tenets/core/git/blame.py"
},
"evidence": "me result = subprocess.run(cmd, cwd=repo_path, capture_output=True, text=True, check=True) # Pa",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tenets/core/git/blame.py",
"line": 399,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (tenets/core/git/stats.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tenets/core/git/stats.py:526`): 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": "tenets/core/git/stats.py"
},
"evidence": "result = subprocess.run( [\"git\", \"log\", \"--reverse\", \"--format=%at\", \"-1\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tenets/core/git/stats.py",
"line": 526,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (tenets/storage/cache.py)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`tenets/storage/cache.py:130`): 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": "tenets/storage/cache.py"
},
"evidence": "return pickle.loads(value_blob) # nosec except Exception as e: sel",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "tenets/storage/cache.py",
"line": 130,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "tenets_search_tools",
"tags": [],
"reasons": {}
},
{
"tool": "tenets_get_tool_schema",
"tags": [],
"reasons": {}
},
{
"tool": "tenets_distill",
"tags": [],
"reasons": {}
},
{
"tool": "tenets_rank_files",
"tags": [],
"reasons": {}
},
{
"tool": "tenets_examine",
"tags": [],
"reasons": {}
},
{
"tool": "tenets_chronicle",
"tags": [],
"reasons": {}
},
{
"tool": "tenets_momentum",
"tags": [],
"reasons": {}
},
{
"tool": "tenets_session",
"tags": [],
"reasons": {}
},
{
"tool": "tenets_tenet",
"tags": [],
"reasons": {}
},
{
"tool": "tenets_system_instruction",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "875abe5d10bbb4c1e2d916d0de7f7ca968b175837012029821dfce95285dd63f",
"stats": {
"tools": 10,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 8,
"medium": 1,
"low": 0,
"info": 0
}
}
}