Terradev
Provisions GPU instances and manages Kubernetes clusters across multiple cloud providers via Terradev CLI.
0Tools
14Findings
5Stars
Mar 22, 2026Last Scanned
4 critical · 7 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
100%2 rules
Injection via prompt templates and runtime tool output
Findings14
4critical
7high
2medium
1low
Critical4
criticalC1Command InjectionMCP03-command-injectionAML.T0054
Pattern "exec\s*\(" matched in source_code: "exec(" (at position 10099)
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.
criticalK5Auto-Approve / Bypass Confirmation PatternMCP06-excessive-permissionsAML.T0054
Pattern "(auto|automatic)[_\s-]?(approv|confirm|accept|consent|yes)" matched in source_code: "auto-approv" (at position 17061)
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.
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 23)
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.
criticalQ11Code Suggestion Poisoning via MCPMCP01-prompt-injectionAML.T0054.001
Pattern "(?:suggest|generate|complete|insert).*(?:code|function|class|import|require)" matched in source_code: "Complete Agentic GPU Infrastructure for Claude Code" (at position 90)
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.
High7
highK4Missing Human Confirmation for Destructive OpsMCP06-excessive-permissionsAML.T0054
Pattern "(auto[_\s-]?execute|auto[_\s-]?approve|skip[_\s-]?confirm|no[_\s-]?prompt)" matched in source_code: "auto-approve" (at position 17061)
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.
highL15Update Notification SpoofingMCP02-tool-poisoningAML.T0054
Pattern "(?:please|you\s+(?:need|should|must))\s+(?:run|execute|install).*(?:npm|pip|npx|curl|wget)" matched in source_code: "Please install it with: pip" (at position 1680)
MCP servers should not include update commands in tool descriptions or responses. Use standard package manager update mechanisms (npm update, pip install --upgrade). Never download update scripts from URLs. Implement signed update verification. AI clients should refuse to execute install commands suggested by tool responses.
highP9Missing Container Resource LimitsMCP07-insecure-configT1499.001
Pattern "(?:for|while)\s*[^}]*(?:fs\.writeFile|open\s*\([^)]*["']w|createWriteStream)(?!.*(?:limit|max|count|quota))" matched in source_code: "form configuration for parallel provisioning
terraform_config = generate_terraform_config(gpu_type, count, providers, max_price)
# Write main.tf
main_tf_path = os.path.join(ws_dir, "main.tf")
with open(main_tf_path, 'w') as f:
f.write(terraform_config)
# Write variables.tf
vars_tf_path = os.path.join(ws_dir, "variables.tf")
with open(vars_tf_path, 'w" (at position 15220)
Always set resource limits for MCP server containers: memory (--memory), CPU (--cpus), PIDs (--pids-limit), file descriptors (--ulimit nofile), and open files. In Kubernetes, set both requests and limits in the container spec. Use LimitRange and ResourceQuota at the namespace level as a safety net. Set pids.max in cgroups to prevent fork bombs. A missing PID limit allows a single tool invocation to fork-bomb the host (CVE-2025-26449 class).
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(generate_variables_file" (at position 15681)
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.
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 tool" (at position 28262)
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: "Execute a raw shell command (e.g. SSH) and return" (at position 11357)
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 "(invoke|call|execute)[_\s-]?(?:tool|agent|self)(?!.*(?:depth|level|limit|max[_\s-]?(?:depth|recursi|iter|call)|count))" matched in source_code: "CallTool" (at position 1216)
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.
Medium2
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.info("Loading MCP tool" (at position 28298)
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.
mediumK17Missing Timeout or Circuit BreakerMCP07-insecure-configAML.T0054
Pattern "(?:exec|execSync|spawn|subprocess\.run|os\.system)\s*\((?!.*(?:timeout|kill|maxBuffer|signal))" matched in source_code: "subprocess.run(" (at position 2294)
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.