Specforge — the complete, unedited output of the deterministic mcptrustchecker engine v1.8.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.8.0",
"methodologyVersion": "mcptrustchecker-1.8"
},
"target": {
"id": "specforge-mcp",
"source": {
"kind": "package",
"origin": "specforge-mcp"
},
"server": {
"name": "specforge-mcp"
}
},
"grade": "B",
"score": {
"score": 83,
"threatScore": 91,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 9.45,
"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": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.5,
"appliedPenalty": 3.15
},
{
"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": "none",
"label": "publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read",
"appliedPenalty": 2
},
{
"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-1.8"
},
"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 (32 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-001",
"title": "Dynamic code execution in server code (dist/engine/auditor-security/electron-checks.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engine/auditor-security/electron-checks.js:76`): 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": "dist/engine/auditor-security/electron-checks.js"
},
"evidence": "suggestion: 'Remove all eval() calls. Use JSON.parse() or safer alternatives.', reference: 'Electron Sec",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/engine/auditor-security/electron-checks.js",
"line": 76,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/engine/actuals/git-analyzer.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engine/actuals/git-analyzer.js:3`): 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": "dist/engine/actuals/git-analyzer.js"
},
"evidence": "{ execSync } from 'node:child_process'; const SPEC_ID_PATTERN = /^SPEC-\\d+/; const MAX_SESSION_GAP_MS = 2 * 60 * 60 * 10",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/engine/actuals/git-analyzer.js",
"line": 3,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/engine/dora-metrics/git-log.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engine/dora-metrics/git-log.js: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": "dist/engine/dora-metrics/git-log.js"
},
"evidence": "{ execFile } from 'node:child_process'; import { promisify } from 'node:util'; const execFileAsync = promisify(execFile)",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/engine/dora-metrics/git-log.js",
"line": 2,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/engine/workflow-validator/git-flow.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engine/workflow-validator/git-flow.js:3`): 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": "dist/engine/workflow-validator/git-flow.js"
},
"evidence": "{ execSync } from 'node:child_process'; // === Helpers === function runGit(args, cwd) { try { return execSyn",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/engine/workflow-validator/git-flow.js",
"line": 3,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/engine/actuals/git-analyzer.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/engine/actuals/git-analyzer.js:158`): 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": "dist/engine/actuals/git-analyzer.js"
},
"evidence": "const result = execSync(`git log --format=\"%H|%aI|%s\" --numstat --all --grep=\"${specId}\"`, { cwd: p",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/engine/actuals/git-analyzer.js",
"line": 158,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/engine/workflow-validator/git-flow.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/engine/workflow-validator/git-flow.js:7`): 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": "dist/engine/workflow-validator/git-flow.js"
},
"evidence": "try { return execSync(`git ${args}`, { cwd, encoding: 'utf-8', stdio: ['p",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/engine/workflow-validator/git-flow.js",
"line": 7,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (dist/tools/git/git-helpers.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`dist/tools/git/git-helpers.js: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": "dist/tools/git/git-helpers.js"
},
"evidence": "execFileCb } from 'node:child_process'; import { promisify } from 'node:util'; import { knowledgeStore } from '../../sto",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/tools/git/git-helpers.js",
"line": 2,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"specforge-mcp\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
"remediation": "Prefer packages that link to public, reviewable source.",
"location": {
"kind": "package",
"name": "specforge-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "check_config_health",
"tags": [],
"reasons": {}
},
{
"tool": "generate_adr",
"tags": [],
"reasons": {}
},
{
"tool": "design_schema",
"tags": [],
"reasons": {}
},
{
"tool": "define_ui_contract",
"tags": [],
"reasons": {}
},
{
"tool": "challenge_spec",
"tags": [],
"reasons": {}
},
{
"tool": "generate_execution_plan",
"tags": [],
"reasons": {}
},
{
"tool": "suggest_stack",
"tags": [],
"reasons": {}
},
{
"tool": "check_versions",
"tags": [],
"reasons": {}
},
{
"tool": "generate_skill",
"tags": [],
"reasons": {}
},
{
"tool": "detect_agent",
"tags": [],
"reasons": {}
},
{
"tool": "generate_sub_agent",
"tags": [],
"reasons": {}
},
{
"tool": "generate_rules",
"tags": [],
"reasons": {}
},
{
"tool": "generate_orchestration_script",
"tags": [],
"reasons": {}
},
{
"tool": "detect_drift",
"tags": [],
"reasons": {}
},
{
"tool": "summarize_spec",
"tags": [],
"reasons": {}
},
{
"tool": "generate_checklist",
"tags": [],
"reasons": {}
},
{
"tool": "reconcile_spec",
"tags": [],
"reasons": {}
},
{
"tool": "learn_pattern",
"tags": [],
"reasons": {}
},
{
"tool": "audit",
"tags": [],
"reasons": {}
},
{
"tool": "consult_docs",
"tags": [],
"reasons": {}
},
{
"tool": "discover_mcps",
"tags": [],
"reasons": {}
},
{
"tool": "suggest_mcps",
"tags": [],
"reasons": {}
},
{
"tool": "set_locale",
"tags": [],
"reasons": {}
},
{
"tool": "init_project",
"tags": [],
"reasons": {}
},
{
"tool": "init_constitution",
"tags": [],
"reasons": {}
},
{
"tool": "clarify_requirements",
"tags": [],
"reasons": {}
},
{
"tool": "create_spec",
"tags": [],
"reasons": {}
},
{
"tool": "list_specs",
"tags": [],
"reasons": {}
},
{
"tool": "update_status",
"tags": [],
"reasons": {}
},
{
"tool": "estimate",
"tags": [],
"reasons": {}
},
{
"tool": "reverse_engineer",
"tags": [],
"reasons": {}
},
{
"tool": "validate",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "96ece00a3c9b50ef62ff91b3ab59f95dc0c6d68b7aa9202b18de9c1d2671ff26",
"stats": {
"tools": 32,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 2,
"low": 1,
"info": 1
}
}
}