Cortex — 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": "@rikaidev/cortex",
"source": {
"kind": "package",
"origin": "@rikaidev/cortex"
},
"server": {
"name": "@rikaidev/cortex"
}
},
"grade": "C",
"score": {
"score": 79,
"threatScore": 86,
"grade": "C",
"band": "C",
"categorySubtotals": {
"injection": 14.18,
"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": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.25,
"appliedPenalty": 1.58
},
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.1,
"appliedPenalty": 0.63
},
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.1,
"appliedPenalty": 0.63
},
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.1,
"appliedPenalty": 0.63
},
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.1,
"appliedPenalty": 0.63
},
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.1,
"appliedPenalty": 0.63
},
{
"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 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 (35 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/core/mcp/services/pr-review-service.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/core/mcp/services/pr-review-service.js:352`): 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/core/mcp/services/pr-review-service.js"
},
"evidence": "l\\s*\\(/, issue: \"Use of eval() is a security risk\" }, { regex: /innerHTML\\s*=/,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/core/mcp/services/pr-review-service.js",
"line": 352,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/core/mcp/services/security-service.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/core/mcp/services/security-service.js:213`): 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/core/mcp/services/security-service.js"
},
"evidence": "remediation: \"Avoid eval(). Use safer alternatives like JSON.parse()\", owasp: \"A03:2021-Injection\",",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/core/mcp/services/security-service.js",
"line": 213,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (src/core/mcp/services/pr-review-service.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/core/mcp/services/pr-review-service.ts:479`): 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": "src/core/mcp/services/pr-review-service.ts"
},
"evidence": "l\\s*\\(/, issue: \"Use of eval() is a security risk\" }, { regex: /innerHTML\\s*=/, issue: \"innerHTML",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "src/core/mcp/services/pr-review-service.ts",
"line": 479,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (src/core/mcp/services/security-service.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/core/mcp/services/security-service.ts:250`): 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": "src/core/mcp/services/security-service.ts"
},
"evidence": "remediation: \"Avoid eval(). Use safer alternatives like JSON.parse()\", owasp: \"A03:2021-Injection\",",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "src/core/mcp/services/security-service.ts",
"line": 250,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/core/mcp/handlers/checkpoint/checkpoint-handler.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/core/mcp/handlers/checkpoint/checkpoint-handler.js:33`): 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/core/mcp/handlers/checkpoint/checkpoint-handler.js"
},
"evidence": "} = await import(\"node:child_process\"); branch = execSync(\"git rev-parse --abbrev-ref HEAD\", {",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/core/mcp/handlers/checkpoint/checkpoint-handler.js",
"line": 33,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/core/mcp/services/change-analyzer.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/core/mcp/services/change-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/core/mcp/services/change-analyzer.js"
},
"evidence": "port { execSync } from \"child_process\"; /** * Service for analyzing code changes from git history and workflows. * *",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/core/mcp/services/change-analyzer.js",
"line": 3,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/core/mcp/services/ci-pipeline-service.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/core/mcp/services/ci-pipeline-service.js:6`): 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/core/mcp/services/ci-pipeline-service.js"
},
"evidence": "{ execSync } from \"node:child_process\"; import * as path from \"node:path\"; import fs from \"fs-extra\"; /** * Service for",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/core/mcp/services/ci-pipeline-service.js",
"line": 6,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/core/mcp/services/gitignore-validator.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/core/mcp/services/gitignore-validator.js: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": "dist/core/mcp/services/gitignore-validator.js"
},
"evidence": "import { exec } from \"child_process\"; import { promisify } from \"util\"; import * as fs from \"fs-extra\"; import * as pa",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/core/mcp/services/gitignore-validator.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/core/mcp/services/implementation-validator.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/core/mcp/services/implementation-validator.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/core/mcp/services/implementation-validator.js"
},
"evidence": "port { execSync } from \"child_process\"; import { DangerZoneService } from \"./danger-zone-service.js\"; import { Environme",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/core/mcp/services/implementation-validator.js",
"line": 3,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/core/mcp/services/pr-review-service.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/core/mcp/services/pr-review-service.js:8`): 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/core/mcp/services/pr-review-service.js"
},
"evidence": "port { execSync } from \"child_process\"; /** * Service for automating pull request reviews. * * Reviews PRs against te",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/core/mcp/services/pr-review-service.js",
"line": 8,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/core/mcp/services/project-detector.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/core/mcp/services/project-detector.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/core/mcp/services/project-detector.js"
},
"evidence": "port { execSync } from \"child_process\"; /** * Service for detecting project conventions and configuration. * * Analyz",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/core/mcp/services/project-detector.js",
"line": 3,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/core/mcp/services/security-service.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/core/mcp/services/security-service.js:8`): 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/core/mcp/services/security-service.js"
},
"evidence": "port { execSync } from \"child_process\"; import { v4 as uuidv4 } from \"uuid\"; /** * Service for security scanning and vu",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/core/mcp/services/security-service.js",
"line": 8,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/core/mcp/services/team-knowledge-service.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/core/mcp/services/team-knowledge-service.js:8`): 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/core/mcp/services/team-knowledge-service.js"
},
"evidence": "port { execSync } from \"child_process\"; import { v4 as uuidv4 } from \"uuid\"; /** * Service for managing team knowledge",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/core/mcp/services/team-knowledge-service.js",
"line": 8,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/core/mcp/services/template-generator.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/core/mcp/services/template-generator.js:61`): 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/core/mcp/services/template-generator.js"
},
"evidence": "} = await import(\"node:child_process\"); const branch = execSync(\"git rev-parse --abbrev-ref HEAD\", {",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/core/mcp/services/template-generator.js",
"line": 61,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/core/mcp/services/change-analyzer.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/core/mcp/services/change-analyzer.js:61`): 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/core/mcp/services/change-analyzer.js"
},
"evidence": "const log = execSync(`git log ${range} --format=%H|||%s|||%b|||%n|||`, { cwd: this.projectRo",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/core/mcp/services/change-analyzer.js",
"line": 61,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/core/mcp/services/ci-pipeline-service.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/core/mcp/services/ci-pipeline-service.js:45`): 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/core/mcp/services/ci-pipeline-service.js"
},
"evidence": "const result = execSync(`gh ${args}`, { cwd: this.projectRoot, encoding: \"utf-8",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/core/mcp/services/ci-pipeline-service.js",
"line": 45,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/core/mcp/services/pr-review-service.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/core/mcp/services/pr-review-service.js:167`): 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/core/mcp/services/pr-review-service.js"
},
"evidence": "const prJson = execSync(`gh pr view ${prNumber} --json number,title,body,author,baseRefName,headRefName,state,f",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/core/mcp/services/pr-review-service.js",
"line": 167,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/core/mcp/services/team-knowledge-service.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/core/mcp/services/team-knowledge-service.js:115`): 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/core/mcp/services/team-knowledge-service.js"
},
"evidence": "const reviewsJson = execSync(`gh pr view ${prNumber} --json reviews,comments`, { cwd: this.projectRo",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/core/mcp/services/team-knowledge-service.js",
"line": 115,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (src/core/mcp/services/change-analyzer.ts)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/core/mcp/services/change-analyzer.ts:99`): 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": "src/core/mcp/services/change-analyzer.ts"
},
"evidence": "EAD\"; const log = execSync(`git log ${range} --format=%H|||%s|||%b|||%n|||`, { cwd: this.projectRoot,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "src/core/mcp/services/change-analyzer.ts",
"line": 99,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (src/core/mcp/services/ci-pipeline-service.ts)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/core/mcp/services/ci-pipeline-service.ts:73`): 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": "src/core/mcp/services/ci-pipeline-service.ts"
},
"evidence": "{ const result = execSync(`gh ${args}`, { cwd: this.projectRoot, encoding: \"utf-8\", stdio",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "src/core/mcp/services/ci-pipeline-service.ts",
"line": 73,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (src/core/mcp/services/pr-review-service.ts)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/core/mcp/services/pr-review-service.ts:223`): 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": "src/core/mcp/services/pr-review-service.ts"
},
"evidence": "{ const prJson = execSync( `gh pr view ${prNumber} --json number,title,body,author,baseRefName,headRefNam",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "src/core/mcp/services/pr-review-service.ts",
"line": 223,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (src/core/mcp/services/team-knowledge-service.ts)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/core/mcp/services/team-knowledge-service.ts:162`): 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": "src/core/mcp/services/team-knowledge-service.ts"
},
"evidence": "const reviewsJson = execSync( `gh pr view ${prNumber} --json reviews,comments`, { cwd: thi",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "src/core/mcp/services/team-knowledge-service.ts",
"line": 162,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "enhance-context",
"tags": [],
"reasons": {}
},
{
"tool": "record-experience",
"tags": [],
"reasons": {}
},
{
"tool": "create-workflow",
"tags": [],
"reasons": {}
},
{
"tool": "execute-workflow-role",
"tags": [],
"reasons": {}
},
{
"tool": "Cortex Workflows",
"tags": [],
"reasons": {}
},
{
"tool": "Workflow Handoff",
"tags": [],
"reasons": {}
},
{
"tool": "Workflow PR",
"tags": [],
"reasons": {}
},
{
"tool": "Project Snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "Workflow Snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "Project Tasks",
"tags": [],
"reasons": {}
},
{
"tool": "IDE Integration Guide",
"tags": [],
"reasons": {}
},
{
"tool": "Memory Index",
"tags": [],
"reasons": {}
},
{
"tool": "Memory Experiences by Type",
"tags": [],
"reasons": {}
},
{
"tool": "Memory Search",
"tags": [],
"reasons": {}
},
{
"tool": "spec",
"tags": [],
"reasons": {}
},
{
"tool": "description",
"tags": [],
"reasons": {}
},
{
"tool": "clarify",
"tags": [],
"reasons": {}
},
{
"tool": "workflowId",
"tags": [],
"reasons": {}
},
{
"tool": "plan",
"tags": [],
"reasons": {}
},
{
"tool": "review",
"tags": [],
"reasons": {}
},
{
"tool": "tasks",
"tags": [],
"reasons": {}
},
{
"tool": "implement",
"tags": [],
"reasons": {}
},
{
"tool": "decompose-task",
"tags": [],
"reasons": {}
},
{
"tool": "taskId",
"tags": [],
"reasons": {}
},
{
"tool": "taskDescription",
"tags": [],
"reasons": {}
},
{
"tool": "validate-implementation",
"tags": [],
"reasons": {}
},
{
"tool": "changedFiles",
"tags": [],
"reasons": {}
},
{
"tool": "release",
"tags": [],
"reasons": {}
},
{
"tool": "version",
"tags": [],
"reasons": {}
},
{
"tool": "tag",
"tags": [],
"reasons": {}
},
{
"tool": "push",
"tags": [],
"reasons": {}
},
{
"tool": "onboard",
"tags": [],
"reasons": {}
},
{
"tool": "status",
"tags": [],
"reasons": {}
},
{
"tool": "list",
"tags": [],
"reasons": {}
},
{
"tool": "limit",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "9c1a4577628c5013d4d6e9cbf1cfc4d6287ae03300fc812c4374c070e18a56ad",
"stats": {
"tools": 35,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 14,
"medium": 8,
"low": 0,
"info": 0
}
}
}