Sumo Qa — 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": "sumo-qa",
"source": {
"kind": "package",
"origin": "sumo-qa"
},
"server": {
"name": "sumo-qa"
}
},
"grade": "A",
"score": {
"score": 92,
"threatScore": 99,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 0,
"exfiltration": 1.2,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-008",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"rawWeight": 3,
"confidenceMult": 0.4,
"diminishingFactor": 1,
"appliedPenalty": 1.2
},
{
"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": [
"ingests untrusted external content (a prompt-injection entry point)",
"can execute shell commands or code"
],
"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 (30 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 (.claude/hooks/validate-on-content-edit.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`.claude/hooks/validate-on-content-edit.py:72`): 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": ".claude/hooks/validate-on-content-edit.py"
},
"evidence": "return 0 result = subprocess.run( [\"sumo-qa-validate\"], cwd=repo_root, capture_output=True",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": ".claude/hooks/validate-on-content-edit.py",
"line": 72,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/sumo_qa/doctor.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/sumo_qa/doctor.py:238`): 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/sumo_qa/doctor.py"
},
"evidence": "rams\": {}}) proc = subprocess.Popen( # noqa: S603 -- argv comes from a trusted McpCommand mcp_cmd.as_subpr",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/sumo_qa/doctor.py",
"line": 238,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/sumo_qa/external_skills.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/sumo_qa/external_skills.py:188`): 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/sumo_qa/external_skills.py"
},
"evidence": "ry: completed = subprocess.run( command, capture_output=True, check=False,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/sumo_qa/external_skills.py",
"line": 188,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (src/sumo_qa/repo_map_resolvers/typescript.py)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`src/sumo_qa/repo_map_resolvers/typescript.py:551`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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/sumo_qa/repo_map_resolvers/typescript.py"
},
"evidence": "g literal (a computed ``require(name)`` / ``import(expr)`` cannot be resolved statically). \"\"\" c",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "src/sumo_qa/repo_map_resolvers/typescript.py",
"line": 551,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-008",
"title": "Hardcoded GitHub token in test/example/packaging (tests/test_feedback_memory.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "A hardcoded GitHub token (a live-looking credential hardcoded in shipped code) appears in `tests/test_feedback_memory.py:347`. Verify whether this is a real credential; if so, remove and rotate it.",
"remediation": "Remove the secret, rotate it, and load credentials from the environment or a secret store.",
"location": {
"kind": "server",
"name": "tests/test_feedback_memory.py"
},
"evidence": "GitHub token: ghp_…(redacted)",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"secretType": "github-token",
"file": "tests/test_feedback_memory.py",
"line": 347
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in packaging/dev tooling (tests/test_route_qa_runners.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_route_qa_runners.py:406`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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_route_qa_runners.py"
},
"evidence": "positives; a first-line eval (the common case) still routes. This pins the accepted trailing-line miss.",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/test_route_qa_runners.py",
"line": 406,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (.claude/skills/regen-eval-baseline/scripts/run_baseline.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/regen-eval-baseline/scripts/run_baseline.py:448`): 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": ".claude/skills/regen-eval-baseline/scripts/run_baseline.py"
},
"evidence": "in(cmd)}\") result = subprocess.run(cmd, cwd=repo_root) if result.returncode != 0: print( f\"\\",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": ".claude/skills/regen-eval-baseline/scripts/run_baseline.py",
"line": 448,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/check_codeblock_file_refs.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/check_codeblock_file_refs.py:71`): 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": "scripts/check_codeblock_file_refs.py"
},
"evidence": "> list[Path]: out = subprocess.check_output( [\"git\", \"ls-files\", \"*.md\"], cwd=repo_root, tex",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/check_codeblock_file_refs.py",
"line": 71,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/check_mutation_gate.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/check_mutation_gate.py:186`): 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": "scripts/check_mutation_gate.py"
},
"evidence": "list[str]: result = subprocess.run( [\"git\", \"diff\", \"--name-only\", \"--no-renames\", spec], capture_ou",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/check_mutation_gate.py",
"line": 186,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/dev_install.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/dev_install.py:66`): 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": "scripts/dev_install.py"
},
"evidence": "lush=True) result = subprocess.run(argv, check=False) if check and result.returncode != 0: print(f\"\\n[de",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/dev_install.py",
"line": 66,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/generate_marketplace_assets.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/generate_marketplace_assets.py:220`): 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": "scripts/generate_marketplace_assets.py"
},
"evidence": "). \"\"\" result = subprocess.run( [sys.executable, \"-m\", \"sumo_qa.doctor\"], capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/generate_marketplace_assets.py",
"line": 220,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/regen_tools_list_snapshot.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/regen_tools_list_snapshot.py:29`): 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": "scripts/regen_tools_list_snapshot.py"
},
"evidence": "lse src_path return subprocess.Popen( [sys.executable, \"-m\", \"sumo_qa\"], stdin=subprocess.PIPE,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/regen_tools_list_snapshot.py",
"line": 29,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/uvx_smoke_handshake.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/uvx_smoke_handshake.py:96`): 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": "scripts/uvx_smoke_handshake.py"
},
"evidence": "RED\"] = \"1\" proc = subprocess.Popen( # noqa: S603 -- cmd is caller-controlled cmd, stdin=subproces",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/uvx_smoke_handshake.py",
"line": 96,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal in packaging/dev tooling (tests/test_repo_map_resolvers_typescript.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_repo_map_resolvers_typescript.py:163`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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_repo_map_resolvers_typescript.py"
},
"evidence": "js.extract(b\"const x = require(dynamicName);\\n\") == [] @_needs_ts def test_extract_empty_specifier_literal(): # `",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "tests/test_repo_map_resolvers_typescript.py",
"line": 163,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"sumo-qa\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "sumo-qa"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "sumo_qa_explain_test_data_requirements",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_find_test_data",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_validate_test_data",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_register_known_good_test_data",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_ingest_knowledge_pack",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_capture_review_feedback",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_load_classifications",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_load_approaches",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_load_principles",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_load_techniques",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_load_standards",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_load_rules",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_load_catalogue_entry",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_capabilities",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_scan_repo",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_analyze_diff_impact",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_query_repo_map",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_format_risk_ledger",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_format_context_bundle",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_format_qa_scorecard",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_export_test_cases",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_generate_qa_report",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_record_coverage",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_record_mutation",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_search_external_skills",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_check_external_skill_installed",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_install_external_skill",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_execute_external_skill",
"tags": [],
"reasons": {}
},
{
"tool": "sumo_qa_list_skill_manifests",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "sumo_qa_load_skill_context",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "c0552fc06b8c67ef10f33ffb4a0439524d3d1020dc8e6818cec07829e680e7cc",
"stats": {
"tools": 30,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 3,
"medium": 1,
"low": 10,
"info": 1
}
}
}