DOM Analyzer
Analyze web page DOM structure, capture screenshots, and automate browser interactions via Puppeteer.
0Tools
15Findings
0Stars
Mar 24, 2026Last Scanned
4 critical · 9 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
50%2 rules1 found
Injection via prompt templates and runtime tool output
Findings15
4critical
9high
1medium
1low
Critical4
criticalC1Command InjectionMCP03-command-injectionAML.T0054
Pattern "`[^`]+`" matched in source_code: "`Impossibile leggere config ${configPath}, uso valori di default: ${err?.message ?? err}`" (at position 1032)
Replace exec()/execSync() with execFile() and pass arguments as an array, never as a string. Validate all inputs against an allowlist before use in any shell context. For subprocess.run, always pass a list and shell=False.
criticalO2HTTP Header Covert ChannelMCP04-data-exfiltrationAML.T0057
Pattern "(?:Cookie|cookie)\s*[:=]\s*(?:[^'"\s]*(?:\$\{|\+|Buffer|encode|btoa|base64|secret|token|env))" matched in source_code: "cookie = `${" (at position 10000)
Never include application secrets, environment variables, or user data in HTTP headers of outbound requests. Use a strict allowlist of headers for outbound HTTP calls. Log all outbound HTTP requests including full headers for audit purposes. Implement egress filtering that inspects both request bodies AND headers.
criticalQ13MCP Bridge Package Supply Chain AttackMCP10-supply-chainAML.T0054
Pattern "["']@modelcontextprotocol/sdk["']\s*:\s*["'](?:\^|~|\*|latest)" matched in source_code: ""@modelcontextprotocol/sdk": "^" (at position 12630)
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.
criticalN15JSON-RPC Method Name ConfusionMCP05-privilege-escalationAML.T0054
Pattern "(?:method|action)\s*[:=]\s*(?:(?:req|params|body|message|data)\s*\.\s*method)(?!.*(?:allowedMethods|ALLOWED_METHODS|whitelist|allowlist|switch\s*\(|includes\(|has\())" matched in source_code: "method: req.method" (at position 1877)
Validate all JSON-RPC method names against an explicit allowlist. Do not use dynamic dispatch (obj[method]()) for method routing — an attacker can invoke internal methods not intended for external access. Separate tool invocation (tools/call) from protocol methods (initialize, ping). Validate that tools/call only dispatches to registered tool names. Reference: JSON-RPC 2.0 Section 4.1, CWE-749 (Exposed Dangerous Method).
High9
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "zod@3.22.0" has known CVEs:
Update dependencies to versions that patch known CVEs. Run 'npm audit fix' or 'pip-audit' to identify and resolve vulnerable dependencies.
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 initBrowserFromConfig() {
await initBrowser(" (at position 2751)
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.
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: "Config: ServerConfig = { targetUrl: "http" (at position 726)
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.
highQ14Concurrent MCP Server Race ConditionMCP07-insecure-configT1068
Pattern "(?:read|write|modify|delete).*(?:file|path|directory)(?!.*(?:lock|mutex|semaphore|flock|atomic))" matched in source_code: "readFileSync(configPath" (at position 852)
MCP servers sharing filesystem or database backends with other servers must implement proper concurrency controls. Use: (1) file locking (flock/lockfile) for filesystem operations, (2) database transactions for all read-modify-write sequences, (3) atomic file operations (O_EXCL, mkdtemp) instead of check-then-create, (4) lstat() to detect symlinks before following (CVE-2025-53109). Never assume exclusive access to shared resources — other MCP servers may be operating concurrently.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L85 interpolates error variable "err" into response. If the error originates from attacker-controlled input (e.g., malformed data), the error message becomes an injection vector into the AI's context.
Never include user input or LLM manipulation directives in error messages or tool responses. Use structured error codes.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L213 interpolates error variable "err" into response. If the error originates from attacker-controlled input (e.g., malformed data), the error message becomes an injection vector into the AI's context.
Never include user input or LLM manipulation directives in error messages or tool responses. Use structured error codes.
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "@modelcontextprotocol/sdk@1.0.0" has known CVEs:
Update dependencies to versions that patch known CVEs. Run 'npm audit fix' or 'pip-audit' to identify and resolve vulnerable dependencies.
highO6Server Fingerprinting via Error ResponsesMCP04-data-exfiltrationAML.T0057
Pattern "catch\s*\([^)]*\)\s*\{[^}]*(?:res\.(?:send|json)|return).*(?:err(?:or)?\.(?:message|stack|code)|connection|host|port|database)" matched in source_code: "catch (err: any) {
return { content: [{ type: "text", text: `Errore: ${err.message" (at position 7242)
Never expose process, OS, runtime, or database metadata in tool responses or error messages. Use generic error messages ("An error occurred") for production responses. Remove or disable debug/diagnostic endpoints. If health endpoints are needed, limit them to simple "ok"/"error" status without infrastructure details. Wrap all error handlers with a sanitization layer that strips system information.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L32 interpolates error variable "err" into response. If the error originates from attacker-controlled input (e.g., malformed data), the error message becomes an injection vector into the AI's context.
Never include user input or LLM manipulation directives in error messages or tool responses. Use structured error codes.
Medium1
mediumK17Missing Timeout or Circuit BreakerMCP07-insecure-configAML.T0054
Pattern "(?:query|execute|find|select|aggregate)\s*\((?!.*(?:timeout|maxTimeMS|statement_timeout|deadline|cancel))" matched in source_code: "find(" (at position 2001)
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.