Binary Ninja
Integrates with Binary Ninja reverse engineering platform to enable binary analysis tasks like function listing, code decompilation, symbol renaming, and structure analysis through a HTTP server bridge.
0Tools
12Findings
273Stars
Mar 22, 2026Last Scanned
4 critical · 6 high · 1 medium · 1 low findings detected
Security Category Deep Dive
Prompt Injection
Prompt & context manipulation attacks
69
Maturity
14
Rules
5
Sub-Categories
1
Gaps
64%
Implemented
56
Tests
1
Stories
100%3 rules
Injection via tool descriptions and parameter fields
GAP-001Prompt Injection Coverage GapMissing detection coverage for emerging prompt injection attack variants not addressed by current rules
100%4 rules
Hidden instructions via external content and tool responses
100%2 rules
Context window saturation and prior-approval exploitation
100%3 rules
Payload hiding via invisible chars, base64, schema fields
100%2 rules
Injection via prompt templates and runtime tool output
Findings12
4critical
6high
1medium
1low
Critical4
criticalC1Command InjectionMCP03-command-injectionAML.T0054
Pattern "`[^`]+`" matched in source_code: "`[INFO] Calling Binary Ninja server method: ${method}`" (at position 1152)
Replace exec()/execSync() with execFile() and pass arguments as an array, never as a string. Validate all inputs against an allowlist before use in any shell context. For subprocess.run, always pass a list and shell=False.
criticalL7Transitive MCP Server DelegationMCP06-excessive-permissionsAML.T0054
Pattern "(?:proxy|forward|delegate|relay|bridge).*(?:mcp|tool|request).*(?:server|client|upstream)" matched in source_code: "Bridge between MCP and Binary Ninja HTTP Server" (at position 6882)
MCP servers MUST NOT create client connections to other MCP servers without explicit user disclosure. If delegation is required, declare all downstream servers in the server's capabilities and tool descriptions. Never forward user credentials to sub-servers. Implement a trust boundary between the approved server and any delegated servers. Log all transitive delegations for audit.
criticalO5Environment Variable HarvestingMCP04-data-exfiltrationAML.T0057
Pattern "(?:fetch|axios|request|http|https|got|superagent|urllib|httpx).*(?:process\.env|os\.environ|getenv)" matched in source_code: "HTTP_SERVER = process.env" (at position 505)
Never enumerate the entire process environment. Read only the specific environment variables your tool needs by name (e.g., process.env.DATABASE_URL, not process.env). Never return environment variable values in tool responses. Never send environment variable values in outbound HTTP requests. Use a secret management system (HashiCorp Vault, AWS Secrets Manager) instead of environment variables for credentials.
criticalQ13MCP Bridge Package Supply Chain AttackMCP10-supply-chainAML.T0054
Pattern "["']@modelcontextprotocol/sdk["']\s*:\s*["'](?:\^|~|\*|latest)" matched in source_code: ""@modelcontextprotocol/sdk": "^" (at position 7117)
MCP bridge packages (mcp-remote, mcp-proxy, @modelcontextprotocol/sdk, fastmcp) are high-value supply chain targets — CVE-2025-6514 (CVSS 9.6) in mcp-remote affected 437,000+ installs. Always pin exact versions (no ^ or ~ ranges). Use lockfiles (package-lock.json, pnpm-lock.yaml, uv.lock). Never run `npx mcp-remote` without version pinning. Verify package integrity with `npm audit` or `pip-audit` before deployment. Reference: CVE-2025-6514, OWASP ASI04.
High6
highK1Absent Structured LoggingMCP09-logging-monitoringAML.T0054
Pattern "console\.(log|warn|error)\s*\(.*(?:tool|request|handler|execute|invoke)" matched in source_code: "console.error("[INFO] Received ListTools request" (at position 2145)
Implement structured logging (pino, winston, or equivalent) for all tool call handlers. Every tool invocation should log: timestamp, tool name, caller identity, parameters (sanitized), result status, and duration. Required by ISO 27001 A.8.15, CoSAI MCP-T12, and NIST AI RMF MEASURE 2.6.
highK16Unbounded Recursion / Missing Depth LimitsMCP07-insecure-configAML.T0054
Pattern "function\s+(\w+).*\{[^}]*\1\s*\((?!.*(?:depth|level|limit|max|count|recursi))" matched in source_code: "function runServer() {
try {
console.error(`[INFO] Starting Binary Ninja MCP Server (" (at position 6243)
Add explicit depth/recursion limits to all recursive operations. Use iterative approaches where possible. Set maximum depth for directory walking (max_depth=10), tree traversal (max_level=20), and agent re-invocation (max_calls=5). Implement circuit breakers that halt after N iterations. Required by EU AI Act Art. 15 (robustness) and OWASP ASI08.
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "@modelcontextprotocol/sdk@1.0.2" has known CVEs:
Update dependencies to versions that patch known CVEs. Run 'npm audit fix' or 'pip-audit' to identify and resolve vulnerable dependencies.
highK11Missing Server Integrity VerificationMCP10-supply-chainAML.T0054
Pattern "(?:download|fetch|pull).*(?:server|plugin|tool)(?!.*(?:sha256|sha512|checksum|digest|integrity|hash|verify))" matched in source_code: "fetch(`${BN_HTTP_SERVER" (at position 1304)
Implement cryptographic verification for MCP server connections: (1) Pin server TLS certificates or public keys, (2) Verify server tool definition checksums against a known-good manifest, (3) Use package manager integrity checks (npm integrity, pip --require-hashes). The MCP spec recommends but doesn't yet mandate server signing — implement it proactively. Required by ISO 27001 A.8.24 and CoSAI MCP-T6.
highK18Cross-Trust-Boundary Data Flow in Tool ResponseMCP04-data-exfiltrationAML.T0054
Pattern "(?:process\.env|os\.environ|config|settings).*(?:fetch|axios|http|post|send|webhook)" matched in source_code: "process.env.BN_HTTP_SERVER || 'http" (at position 519)
Implement data flow taint tracking: tag data from sensitive sources (databases, credentials, files) and prevent it from flowing to external sinks (HTTP, webhooks, email) without explicit sanitization/redaction. Apply data classification and enforce boundary controls per trust level. Required by ISO 27001 A.5.14 and CoSAI MCP-T5.
highN3JSON-RPC Request ID CollisionMCP07-insecure-configAML.T0054
Pattern "(?:requestId|request_id|id)\s*[:=]\s*(?:Date\.now|time\.time|int\(time|performance\.now)\s*\(" matched in source_code: "id: Date.now(" (at position 1485)
Use cryptographically random or UUID-based request IDs to prevent collision attacks. Do not use sequential integers — an attacker can predict the next ID and inject a response before the legitimate server responds (response spoofing). Validate that response IDs match pending request IDs. Reference: JSON-RPC 2.0 Section 4.1 — 'id' must be unique within a session.
Medium1
mediumK17Missing Timeout or Circuit BreakerMCP07-insecure-configAML.T0054
Pattern "(?:fetch|axios|got|request|urllib|httpx|http\.get|http\.post)\s*\((?!.*(?:timeout|signal|AbortSignal|deadline|cancel))" matched in source_code: "fetch(" (at position 1304)
Add timeouts to ALL external calls: HTTP requests (30s), database queries (10s), subprocess execution (60s), and MCP tool calls (30s). Implement circuit breakers that open after N consecutive failures (e.g., opossum, cockatiel). Use AbortSignal for cancellable operations. Required by EU AI Act Art. 15 and OWASP ASI08.
Low1
lowF4MCP Spec Non-ComplianceMCP07-insecure-config
Server fails MCP spec compliance checks: required:server_name; required:server_version; required:protocol_version; recommended:tool_descriptions; recommended:parameter_descriptions
Follow the MCP specification for server metadata. Include server name, version, and protocol version. Provide descriptions for all tools and parameters.