Universal Code Navigator
Structural code intelligence for AI agents using tree-sitter analysis.
0Tools
19Findings
0Stars
Mar 24, 2026Last Scanned
6 critical · 11 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
50%2 rules1 found
Injection via prompt templates and runtime tool output
Findings19
6critical
11high
1medium
1low
Critical6
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 tokenType === 'comment' || token" (at position 70270)
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.
criticalK5Auto-Approve / Bypass Confirmation PatternMCP06-excessive-permissionsAML.T0054
Pattern "(skip|bypass|disable|suppress|hide)[_\s-]?(user|human)?[_\s-]?(confirm|approv|consent|dialog|prompt|warning)" matched in source_code: "SuppressWarning" (at position 79374)
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.
criticalQ1Dual-Protocol Schema Constraint LossMCP06-excessive-permissionsAML.T0054
Pattern "(?:delete|remove|strip|omit|drop|ignore)\s+(?:pattern|format|minLength|maxLength|constraints)" matched in source_code: "ignore pattern" (at position 96593)
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.
criticalQ11Code Suggestion Poisoning via MCPMCP01-prompt-injectionAML.T0054.001
Pattern "(?:suggest|generate|complete|insert).*(?:code|function|class|import|require)" matched in source_code: "generated files (e.g., Go client-gen, protobuf, code" (at position 25803)
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.
criticalQ13MCP Bridge Package Supply Chain AttackMCP10-supply-chainAML.T0054
Pattern "["']@modelcontextprotocol/sdk["']\s*:\s*["'](?:\^|~|\*|latest)" matched in source_code: ""@modelcontextprotocol/sdk": "^" (at position 135883)
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.
criticalQ9Agentic Workflow DAG ManipulationMCP05-privilege-escalationAML.T0058
Pattern "(?:graph|workflow|pipeline|dag).*(?:modify|update|mutate|alter|change)" matched in source_code: "graph rebuild when incremental rebuild found no change" (at position 21909)
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).
High11
highK13Unsanitized Tool OutputMCP02-tool-poisoningAML.T0054
Pattern "(?:return|respond|result).*(?:readFile|read_file|fs\.read)(?!.*(?:sanitize|escape|encode|strip))" matched in source_code: "return fs.readFile" (at position 14384)
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|orchestrat).*(?:invoke|call|execute|spawn)(?!.*(?:rate[_\s-]?limit|throttle|quota|max[_\s-]?concurrent|semaphore))" matched in source_code: "agents — extract functions, trace call chains, find call" (at position 133740)
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 "function\s+(\w+).*\{[^}]*\1\s*\((?!.*(?:depth|level|limit|max|count|recursi))" matched in source_code: "function extractFunction(code, language, name) {
const result = parse(code, language);
const lines = code.split('\n');
// Exact match first
let fn = result.functions.find(f => f.name === name);
// Fuzzy match if not found
if (!fn) {
const lowerName = name.toLowerCase();
fn = result.functions.find(f =>
f.name.toLowerCase().includes(lowerName) ||
lowerName.includes(f.name.toLowerCase(" (at position 5573)
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.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L621 interpolates error variable "e" 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.
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "@modelcontextprotocol/sdk@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.
highK18Cross-Trust-Boundary Data Flow in Tool ResponseMCP04-data-exfiltrationAML.T0054
Pattern "(?:ssn|social[_\s-]?security|credit[_\s-]?card|bank[_\s-]?account|medical|health).*(?:return|respond|send|post|emit)" matched in source_code: "ssName) { return" (at position 81481)
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.
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: "removeFromCalleeIndex(filePath, oldCached.call" (at position 30815)
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.
highQ14Concurrent MCP Server Race ConditionMCP07-insecure-configT1068
Pattern "(?:read|write|modify|delete).*(?:file|path|directory)(?!.*(?:lock|mutex|semaphore|flock|atomic))" matched in source_code: "readFileSync(filePath" (at position 4978)
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.
highO6Server Fingerprinting via Error ResponsesMCP04-data-exfiltrationAML.T0057
Pattern "(?:res\.(?:send|json)|return|response).*(?:__dirname|__filename|process\.cwd\(\)|path\.resolve|path\.join)" matched in source_code: "return path.resolve" (at position 104513)
Never expose process, OS, runtime, or database metadata in tool responses or error messages. Use generic error messages ("An error occurred") for production responses. Remove or disable debug/diagnostic endpoints. If health endpoints are needed, limit them to simple "ok"/"error" status without infrastructure details. Wrap all error handlers with a sanitization layer that strips system information.
highC15Timing Attack on Secret ComparisonMCP07-insecure-configAML.T0054
[AST pattern] String equality (===) on "hash" at L679 — timing side-channel. Attackers can determine secret value byte-by-byte by measuring comparison time.
Use crypto.timingSafeEqual() or hmac.compare_digest() for secret comparison. Never use === on secrets.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L608 interpolates error variable "e" 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.
Medium1
mediumK17Missing Timeout or Circuit BreakerMCP07-insecure-configAML.T0054
Pattern "(?:query|execute|find|select|aggregate)\s*\((?!.*(?:timeout|maxTimeMS|statement_timeout|deadline|cancel))" matched in source_code: "find(" (at position 5756)
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.