AgentBay
Provides serverless cloud infrastructure for AI agents.
0Tools
9Findings
7Stars
Mar 22, 2026Last Scanned
4 critical · 3 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
Findings9
4critical
3high
1medium
1low
Critical4
criticalC1Command InjectionMCP03-command-injectionAML.T0054
Pattern "`[^`]+`" matched in source_code: "`${baseUrl}/v2/sse?APIKEY=${config.APIKEY}&IMAGEID=${config.IMAGEID}`" (at position 1448)
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.
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 static tools if no API key" (at position 2065)
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 "(?:import|require).*(?:@modelcontextprotocol/sdk.*client|mcp.*client)" matched in source_code: "import { SSEClientTransport } from "@modelcontextprotocol/sdk/client" (at position 100)
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.
criticalQ13MCP Bridge Package Supply Chain AttackMCP10-supply-chainAML.T0054
Pattern "["']@modelcontextprotocol/sdk["']\s*:\s*["'](?:\^|~|\*|latest)" matched in source_code: ""@modelcontextprotocol/sdk": "^" (at position 3125)
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.
High3
highK16Unbounded Recursion / Missing Depth LimitsMCP07-insecure-configAML.T0054
Pattern "(invoke|call|execute)[_\s-]?(?:tool|agent|self)(?!.*(?:depth|level|limit|max[_\s-]?(?:depth|recursi|iter|call)|count))" matched in source_code: "CallTool" (at position 279)
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.
highC3Server-Side Request Forgery (SSRF)MCP04-data-exfiltrationAML.T0057
Pattern "new\s+URL\s*\(\s*(?:req|request|input|param|params|args|url|uri|href|link|target|destination|endpoint|host|address|resource|src|source)" matched in source_code: "new URL(target" (at position 1566)
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@1.12.1" has known CVEs:
Update dependencies to versions that patch known CVEs. Run 'npm audit fix' or 'pip-audit' to identify and resolve vulnerable dependencies.
Medium1
mediumK17Missing Timeout or Circuit BreakerMCP07-insecure-configAML.T0054
Pattern "(?:callTool|invoke|tools\/call|execute_tool)\s*\((?!.*(?:timeout|signal|deadline|cancel|abort))" matched in source_code: "callTool(" (at position 2668)
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.