0/100
0Tools
13Findings
1Stars
—Downloads
Mar 24, 2026Last Scanned
Score Breakdown5 categories
Code75
Dependencies85
Config0
Description100
Behavior100
OWASP MCP Top 10 Coverage
MCP10-supply-chainMCP10-supply-chainFail
MCP02-tool-poisoningMCP02-tool-poisoningFail
MCP07-insecure-configMCP07-insecure-configFail
MCP08-dependency-vulnMCP08-dependency-vulnFail
MCP01-prompt-injectionMCP01-prompt-injectionFail
MCP03-command-injectionMCP03-command-injectionFail
MCP04-data-exfiltrationMCP04-data-exfiltrationFail
MCP09-logging-monitoringMCP09-logging-monitoringPass
MCP05-privilege-escalationMCP05-privilege-escalationPass
MCP06-excessive-permissionsMCP06-excessive-permissionsFail
Findings13
4critical
8high
0medium
1low
0informational
criticalQ13MCP Bridge Package Supply Chain AttackMCP10-supply-chainAML.T0054
Pattern "["']@modelcontextprotocol/sdk["']\s*:\s*["'](?:\^|~|\*|latest)" matched in source_code: ""@modelcontextprotocol/sdk": "^" (at position 36528)
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.
criticalJ7OpenAPI Specification Field InjectionMCP03-command-injectionAML.T0054
Pattern "(?:summary|operationId|description).*\$\{|`.*(?:summary|operationId)" matched in source_code: "`Cleaning History Summary" (at position 11980)
Sanitize all OpenAPI specification fields before using them in code generation or template interpolation. Treat summary, description, operationId, and extension fields as untrusted input. Use parameterized templates instead of string interpolation. See CVE-2026-22785/23947.
criticalK5Auto-Approve / Bypass Confirmation PatternMCP06-excessive-permissionsAML.T0054
Pattern "(no|without)[_\s-]?(user|human)?[_\s-]?(confirm|approv|consent|interaction|intervention)" matched in source_code: "without confirm" (at position 3753)
Never auto-approve or bypass human confirmation for operations with side effects. Implement explicit confirmation gates that cannot be programmatically bypassed. If batch/CI mode is needed, require an explicit opt-in flag with audit logging. Required by EU AI Act Art. 14 (human oversight) and OWASP ASI09.
criticalC1Command InjectionMCP03-command-injectionAML.T0054
Pattern "child_process" matched in source_code: "child_process" (at position 721)
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.
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 waitForResponse(timeoutMs = 5000) {
const startTime = Date.now();
while (Date.now() - startTime < timeoutMs) {
// Check all possible response file locations
for (const responseFile of RESPONSE_FILES) {
try {
if (fs.existsSync(responseFile)) {
const stat = fs.statSync(responseFile);
// Check if file was modified recently (within last 10 seconds)
if (Date.now(" (at position 1296)
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.
highK4Missing Human Confirmation for Destructive OpsMCP06-excessive-permissionsAML.T0054
Pattern "(delete|remove|drop|truncate|destroy|purge|wipe|erase).*(?:execute|run|perform|call)(?!.*(?:confirm|approve|prompt|ask|verify|consent))" matched in source_code: "deletes files immediately without confirmation. Always run one_touch_scan first and get user approval before call" (at position 3727)
All destructive operations (delete, drop, overwrite, send) MUST include a human confirmation step. Use the MCP destructiveHint annotation to signal that client-side confirmation is required. Implement an approval gate pattern: preview changes → request confirmation → execute. Required by ISO 42001 A.9.1, EU AI Act Art. 14, and NIST AI RMF GOVERN 1.7.
highO10Privacy-Violating TelemetryMCP04-data-exfiltrationAML.T0057
Pattern "(?:os\.(?:type|release|platform|arch|hostname|cpus|networkInterfaces|userInfo|homedir)|process\.(?:arch|platform|ppid))\s*\(?" matched in source_code: "os.homedir(" (at position 1003)
Minimize data collection to only what is strictly necessary for tool functionality. Never collect OS fingerprints, hardware IDs, network interface details, or unique device identifiers without explicit user consent. Remove all tracking pixels, analytics beacons, and behavioral profiling code. If telemetry is needed, make it opt-in only, clearly documented, and limited to non-identifying aggregated metrics. Comply with GDPR data minimization (Art. 5(1)(c)) and EU AI Act transparency requirements (Art. 52).
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(responseFile" (at position 1848)
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 L932 interpolates error variable "error" 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.
highK13Unsanitized Tool OutputMCP02-tool-poisoningAML.T0054
Pattern "(?:query|execute|select|find).*(?:return|respond|result|rows|data)(?!.*(?:sanitize|escape|encode|map|filter|select|pick))" matched in source_code: "Find large files on the Mac. Return" (at position 5591)
Sanitize all external data before including in tool responses. Implement output encoding that neutralizes prompt injection patterns. Truncate excessively long content. Validate structure before passing database results. Apply the principle: treat all external data as untrusted, even in tool outputs. Required by CoSAI MCP-T4.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L427 interpolates error variable "error" 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.
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.
Security Category Deep Dive
Sub-Category Tree · Remediation Roadmap · Attack Stories · Compliance Overlay · ATLAS Techniques · Maturity Model
Prompt Injection
Prompt & context manipulation attacks
69
MATURITY
14
RULES
5
SUB-CATS
1
GAPS
64%
IMPL.
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