mcp-code-mode
Sandboxed Python code execution with DSpy-powered reasoning that orchestrates external tools through generated code, featuring configurable security policies and timeout handling.
0Tools
18Findings
22Stars
—Downloads
Mar 22, 2026Last Scanned
Findings18
8critical
9high
0medium
1low
0informational
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: "os.environ.get("OPENAI_API_KEY" (at position 4057)
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.
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 138)
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.
criticalJ1Cross-Agent Configuration PoisoningMCP05-privilege-escalationAML.T0054
Pattern "write.*(mcp[_\s-]?config|mcpServers|mcp_servers)" matched in source_code: "Write MCP config" (at position 1443)
MCP servers MUST NOT write to AI agent configuration directories. If configuration management is the server's purpose, require explicit user confirmation before any write and restrict paths to the server's own config namespace. CVE-2025-53773 demonstrated this enables full RCE across agent boundaries.
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 "⚠️ Error: Please provide an OpenAI or Gemini API Key" (at position 1160)
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 "(?:connect|initialize).*(?:mcp|modelcontextprotocol).*(?:server|endpoint|url)" matched in source_code: "Connects to the MCP server" (at position 1021)
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 "(?:Object\.keys|JSON\.stringify|vars|dict)\s*\(\s*(?:process\.env|os\.environ)\s*\)" matched in source_code: "dict(os.environ)" (at position 1775)
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.
criticalO5Environment Variable HarvestingMCP04-data-exfiltrationAML.T0057
Pattern "os\.environ(?:\.copy\(\)|(?!\[|\.))" matched in source_code: "os.environ" (at position 1780)
Never enumerate the entire process environment. Read only the specific environment variables your tool needs by name (e.g., process.env.DATABASE_URL, not process.env). Never return environment variable values in tool responses. Never send environment variable values in outbound HTTP requests. Use a secret management system (HashiCorp Vault, AWS Secrets Manager) instead of environment variables for credentials.
criticalQ1Dual-Protocol Schema Constraint LossMCP06-excessive-permissionsAML.T0054
Pattern "(openai|function[_\s-]?calling|tool[_\s-]?choice).{0,60}(mcp|model[_\s-]?context)" matched in source_code: "openai_key: str, gemini_key: str, mcp" (at position 957)
Dual-protocol MCP servers must validate input constraints server-side, not rely on client-side schema enforcement. When translating MCP schemas to OpenAI function-calling format, constraints like `pattern`, `minLength`, `maxLength`, and `format` are silently dropped. Implement server-side Zod/AJV validation on all tool inputs regardless of the calling protocol.
highQ14Concurrent MCP Server Race ConditionMCP07-insecure-configT1068
Pattern "(?:read|write|modify|delete).*(?:file|path|directory)(?!.*(?:lock|mutex|semaphore|flock|atomic))" matched in source_code: "Write MCP config to temporary file" (at position 1443)
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.
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "fastmcp@2.0.0" has known CVEs:
Update dependencies to versions that patch known CVEs. Run 'npm audit fix' or 'pip-audit' to identify and resolve vulnerable dependencies.
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "mcp@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.
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "gradio@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 "(connect|load|register|add)[_\s-]?(mcp|server|tool)(?!.*(?:verify|validate|checksum|hash|sign|cert|fingerprint|pin))" matched in source_code: "Load mcp" (at position 539)
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 "(?:readFile|read_file|open).*(?:return|respond|result|content|text)(?!.*(?:sanitize|escape|encode|strip|filter|validate|truncate))" matched in source_code: "openai_input = gr.Text" (at position 3911)
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.
highK15Multi-Agent Collusion PreconditionsMCP05-privilege-escalationAML.T0054
Pattern "(agent|delegate).*(?:send|receive|message|communicate)(?!.*(?:log|audit|trace|record|monitor))" matched in source_code: "agent_task(task_message" (at position 912)
Implement collusion-resistant multi-agent architecture: (1) Verify agent identity cryptographically before accepting commands, (2) Apply ACLs to shared write surfaces, (3) Rate-limit cross-agent invocations, (4) Audit all inter-agent communication with timestamps and agent IDs, (5) Baseline normal interaction patterns for anomaly detection. Required by MAESTRO L7 and CoSAI MCP-T9.
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: "call_tool" (at position 2839)
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.
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "aiohttp@3.9.0" has known CVEs:
Update dependencies to versions that patch known CVEs. Run 'npm audit fix' or 'pip-audit' to identify and resolve vulnerable dependencies.
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.
Tools
No tools exposed by this server.
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-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