Materio Educational Resources
Searches and reads Materio educational PDF resources across semesters, subjects, and topics.
0/100
0Tools
17Findings
0Stars
—Downloads
Mar 24, 2026Last Scanned
Score Breakdown5 categories
Code60
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-escalationFail
MCP06-excessive-permissionsMCP06-excessive-permissionsFail
Findings17
4critical
11high
1medium
1low
0informational
criticalQ9Agentic Workflow DAG ManipulationMCP05-privilege-escalationAML.T0058
Pattern "(?:next[_\s]?(?:step|node|agent)|route[_\s]?to|redirect[_\s]?to|skip[_\s]?(?:step|node|validation))" matched in source_code: "redirectTo" (at position 773)
MCP tools must NOT modify agentic workflow graphs, execution order, or routing during runtime. Workflow structure should be immutable once execution begins. If dynamic workflow modification is required, implement: (1) approval gates that require human confirmation before graph mutations, (2) integrity checks that validate the workflow graph against a known-good baseline after each step, (3) audit logging of all graph modifications with rollback capability. Reference: arXiv 2602.19555, Trend Micro subgraph impersonation attack (2026).
criticalC1Command InjectionMCP03-command-injectionAML.T0054
Pattern "`[^`]+`" matched in source_code: "`node index.js`" (at position 130)
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.
criticalG7DNS-Based Data Exfiltration ChannelMCP04-data-exfiltrationAML.T0040
Pattern "(?:\$\{|\+|concat|format).*\.(?:[a-z0-9-]{3,}\.){1,3}[a-z]{2,6}['"`]" matched in source_code: "${CDN_BASE}/databases/beta/resource.lib.json`" (at position 1827)
Remove all dynamic DNS queries where subdomain content is derived from application data, user input, or system information. DNS exfiltration channels are invisible to most monitoring tools and operate even through strict HTTP firewalls.
If DNS-based service discovery is required, use a static list of known-good hostnames. Never construct DNS query hostnames by concatenating or encoding application data. Deploy DNS logging (e.g., passive DNS, BIND query logs) and alert on high-entropy subdomain queries.
criticalQ13MCP Bridge Package Supply Chain AttackMCP10-supply-chainAML.T0054
Pattern "["']@modelcontextprotocol/sdk["']\s*:\s*["'](?:\^|~|\*|latest)" matched in source_code: ""@modelcontextprotocol/sdk": "^" (at position 27107)
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.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L685 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.
highC3Server-Side Request Forgery (SSRF)MCP04-data-exfiltrationAML.T0057
Pattern "\bfetch\s*\(\s*(?:req|request|input|param|params|args|url|uri|href|link|target|destination|endpoint|host|address|resource|src|source|location|proxy|callback|userUrl|user_url|externalUrl|external_url|redirectUrl|redirect_url)" matched in source_code: "fetch(RESOURCE" (at position 3240)
Validate ALL user-supplied URLs before making HTTP requests:
1. Parse the URL and check the hostname against an explicit allowlist of permitted domains.
2. Block requests to RFC 1918 private ranges: 10.0.0.0/8, 172.16.0.0/12, 192.168.0.0/16.
3. Block loopback (127.0.0.0/8), link-local (169.254.0.0/16), and IPv6 equivalents.
4. Block file:// and other non-http(s) protocols explicitly.
5. Disable automatic redirect following, or re-validate each redirect destination.
6. In cloud environments: block requests to IMDS endpoints (169.254.169.254,
metadata.google.internal) at both the application AND network layer.
Example (Node.js): Use the `ssrf-req-filter` package or implement URL validation
against an allowlist before calling fetch/axios/got.
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "@modelcontextprotocol/sdk@1.6.1" has known CVEs:
Update dependencies to versions that patch known CVEs. Run 'npm audit fix' or 'pip-audit' to identify and resolve vulnerable dependencies.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L526 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.
highN10Incomplete Handshake Denial of ServiceMCP07-insecure-configAML.T0054
Pattern "(?:createServer|listen)\s*\((?!.*(?:maxConnections|maxClients|connectionLimit|MAX_CONN))" matched in source_code: "createServer(" (at position 1041)
Enforce a handshake timeout (recommended: 30 seconds) — terminate connections that do not complete the initialize handshake within the deadline. Limit maximum concurrent pending connections. An attacker can exhaust server connection slots by initiating MCP connections without completing the handshake (Slowloris-style attack). Reference: MCP spec 2025-03-26 lifecycle — initialize MUST complete before functional requests.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L317 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.
highK11Missing Server Integrity VerificationMCP10-supply-chainAML.T0054
Pattern "(connect|load|register|add)[_\s-]?(mcp|server|tool)(?!.*(?:verify|validate|checksum|hash|sign|cert|fingerprint|pin))" matched in source_code: "registerTool" (at position 6798)
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.
highK13Unsanitized Tool OutputMCP02-tool-poisoningAML.T0054
Pattern "(?:fetch|axios|requests?\.get|http\.get).*(?:return|respond|result|body|text|data)(?!.*(?:sanitize|escape|encode|strip|validate|parse|extract))" matched in source_code: "Fetches a PDF from the CDN and extracts its text" (at position 3934)
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.
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 fetchPdfText(url) {
// We MUST encode for the actual HTTP fetch, as some platforms/libraries
// don't handle raw spaces in URLs.
const encodedUrl = new URL(url).toString();
const response = await fetch(" (at position 4002)
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: "truncated ? `> ⚠️ Content trun" (at position 17726)
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.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L412 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.
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 2458)
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.
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