integrate-sdk
Type-safe 3rd party integration SDK for the Integrate MCP server
0Tools
22Findings
Mar 24, 2026Last Scanned
9 critical · 10 high · 2 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
Findings22
9critical
10high
2medium
1low
Critical9
criticalK14Agent Credential Propagation via Shared StateMCP05-privilege-escalationAML.T0054
Pattern "(process\.env|os\.environ|setenv|putenv).*(?:token|credential|api[_\s-]?key|secret|password)" matched in source_code: "process.env.INTEGRATE_API_KEY" (at position 14525)
Never write credentials to shared agent state. Use credential vaults (HashiCorp Vault, AWS Secrets Manager) with per-agent scoped access. Implement OAuth token exchange (RFC 8693) for cross-agent authorization. Redact credentials from all agent outputs before writing to shared memory. Required by OWASP ASI03/ASI07 and MAESTRO L7.
criticalC2Path TraversalMCP05-privilege-escalation
Pattern "\.\./\.\." matched in source_code: "../.." (at position 83884)
Use path.resolve() to canonicalize paths, then verify the result starts with the intended base directory. Reject any input containing '..', null bytes, or encoded variants. Never concatenate user input into file paths.
criticalQ8Cross-Protocol Authentication ConfusionMCP07-insecure-configT1550
Pattern "(?:oauth|bearer).{0,100}(?:api[_\s-]?key|x-api-key|apiKey)" matched in source_code: "OAuth secrets and API key" (at position 13435)
MCP servers supporting multiple protocols must enforce authentication independently per protocol. Never reuse OAuth tokens across protocol boundaries. Implement protocol-specific middleware with explicit auth checks on every path. Audit auth coverage for all transport types (stdio, SSE, Streamable HTTP, REST). Reference: CVE-2025-6514 demonstrated that auth library vulnerabilities in MCP's OAuth layer cascade to all protocols sharing the same auth middleware.
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: "redirect to" (at position 60305)
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).
criticalQ13MCP Bridge Package Supply Chain AttackMCP10-supply-chainAML.T0054
Pattern "(?:mcp|fastmcp|langchain-mcp|llama-index-mcp)(?:>=|~=|==)?(?!\d)" matched in source_code: "MCP" (at position 84)
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.
criticalK8Cross-Boundary Credential SharingMCP05-privilege-escalationAML.T0054
Pattern "(return|respond|output|result).*(?:token|credential|api[_\s-]?key|secret|password|bearer)" matched in source_code: "return config.getProviderToken" (at position 28528)
Never forward, share, or embed credentials across trust boundaries. Use OAuth token exchange (RFC 8693) to create scoped, delegated tokens instead of passing original credentials. Never include credentials in tool responses. Required by ISO 27001 A.5.17 and OWASP ASI03.
criticalL7Transitive MCP Server DelegationMCP06-excessive-permissionsAML.T0054
Pattern "(?:new\s+Client|createClient|MCPClient|StdioClientTransport|SSEClientTransport|StreamableHTTPClientTransport).*(?:server|handler|tool)" matched in source_code: "MCPClientConfig, ReauthContext, ReauthHandler, MCPContext, Tool" (at position 1839)
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.
criticalL9CI/CD Secret Exfiltration PatternsMCP07-insecure-configAML.T0057
Pattern "(?:webhook|callback|notify).*(?:url|endpoint).*(?:process\.env|os\.environ|secrets)" matched in source_code: "CallbackBaseUrl = process.env" (at position 32285)
Never print, log, or transmit CI environment variables containing secrets. Use GitHub Actions '::add-mask::' to prevent accidental secret exposure in logs. Audit all third-party Actions for secret access patterns. Use OIDC tokens instead of long-lived secrets where possible. Restrict secret access to specific workflow jobs and steps. Monitor CI logs for base64-encoded strings.
criticalQ11Code Suggestion Poisoning via MCPMCP01-prompt-injectionAML.T0054.001
Pattern "(?:suggest|generate|complete|insert).*(?:code|function|class|import|require)" matched in source_code: "generateCodeVerifier, generateCode" (at position 465)
MCP tool outputs flowing into IDE code suggestion contexts must be sanitized. Implement output content policies that: (1) strip hidden Unicode characters (zero-width, RTL override, tag characters), (2) detect embedded instructions targeting AI code assistants, (3) validate code blocks against security patterns before they enter the suggestion pipeline, (4) never include shell commands in tool outputs without explicit [COMMAND] markers visible to the user. Reference: IDEsaster (Dec 2025), arXiv 2509.22040.
High10
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L1254 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.
highC11ReDoS VulnerabilityMCP07-insecure-config
Pattern "\([^)]*\)[*+][*+]" matched in source_code: "(Recommended for default client)**" (at position 57699)
Never compile user-supplied strings as regexes. Use a safe regex library (re2, node-re2) for all user-controlled pattern matching — they run in linear time. Bound all input lengths before regex application. Use static analysis tools (safe-regex, vuln-regex-detector) to audit existing patterns.
highC3Server-Side Request Forgery (SSRF)MCP04-data-exfiltrationAML.T0057
Pattern "\bfetch\s*\([^)]*\$\{[^}]*(?:url|uri|host|target|endpoint|param|input|args)[^}]*\}" matched in source_code: "fetch(`${schedulerUrl}/scheduler/register`, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'X-API-KEY': config.apiKey || '',
},
body: JSON.stringify({
triggerId: created.id,
schedule: created.schedule,
callbackUrl: `${callbackBaseUrl}" (at position 32720)
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 "nanoid@3.3.7" has known CVEs:
Update dependencies to versions that patch known CVEs. Run 'npm audit fix' or 'pip-audit' to identify and resolve vulnerable dependencies.
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "ai@4.0.0" has known CVEs:
Update dependencies to versions that patch known CVEs. Run 'npm audit fix' or 'pip-audit' to identify and resolve vulnerable dependencies.
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 configured integrations from server" (at position 80045)
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 "(?:query|execute|select|find).*(?:return|respond|result|rows|data)(?!.*(?:sanitize|escape|encode|map|filter|select|pick))" matched in source_code: "executedAt: executionResult" (at position 39274)
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 storeCodeVerifier(state: string, codeVerifier: string, provider: string, frontendOrigin?: string): void {
// Store for 5 minutes (" (at position 11409)
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: true) to fetch" (at position 25714)
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.
highQ15A2A/MCP Protocol Boundary ConfusionMCP06-excessive-permissionsAML.T0054
Pattern "(?:Task|TaskResult|Message|Part).*(?:tool[_\s-]?(?:input|call|invoke|execute))" matched in source_code: "message || 'Failed to execute tool call" (at position 25479)
Servers bridging A2A and MCP protocols must: (1) sanitize all A2A task metadata before passing to MCP tool inputs, (2) apply MCP content policies to A2A TextPart/FilePart/DataPart content, (3) validate A2A push notifications before they re-enter MCP context, (4) require cryptographic verification for agent discovery and registration (prevent fake agent advertisement — arXiv 2602.19555), (5) maintain separate permission models for A2A and MCP operations — trust in one protocol must not automatically grant trust in the other.
Medium2
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: "request (" (at position 20100)
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.
mediumK20Insufficient Audit Context in LoggingMCP09-logging-monitoringAML.T0054
Pattern "logger\.(info|warn|error)\s*\(.*(?:tool|request|handle|invoke)(?!.*(?:requestId|correlationId|traceId|spanId|agent[_\s-]?id|user[_\s-]?id))" matched in source_code: "logger.error('[MCP Tool" (at position 25377)
Use structured logging that includes all five ISO 27001 A.8.15 fields: (1) WHO — agent/user identity, (2) WHAT — tool name and operation, (3) WHEN — ISO 8601 timestamp, (4) WHERE — server ID and correlation ID, (5) OUTCOME — success/failure and result summary. Replace console.log with structured loggers (pino, winston). Add correlation IDs for request tracing across multi-agent chains.
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.