github-mcp-server-kosta
MCP server for GitHub repository operations with CLI token support
0Tools
19Findings
Mar 24, 2026Last Scanned
5 critical · 11 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
Findings19
5critical
11high
2medium
1low
Critical5
criticalJ7OpenAPI Specification Field InjectionMCP03-command-injectionAML.T0054
Pattern "(?:summary|operationId|description).*\$\{|`.*(?:summary|operationId)" matched in source_code: "description = `${" (at position 81485)
Sanitize all OpenAPI specification fields before using them in code generation or template interpolation. Treat summary, description, operationId, and extension fields as untrusted input. Use parameterized templates instead of string interpolation. See CVE-2026-22785/23947.
criticalC1Command InjectionMCP03-command-injectionAML.T0054
Pattern "execSync\s*\(" matched in source_code: "execSync(" (at position 6660)
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.
criticalQ13MCP Bridge Package Supply Chain AttackMCP10-supply-chainAML.T0054
Pattern "["']@modelcontextprotocol/sdk["']\s*:\s*["'](?:\^|~|\*|latest)" matched in source_code: ""@modelcontextprotocol/sdk": "^" (at position 133181)
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.
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.MCP_HTTP_AUTH_TOKEN" (at position 4002)
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.
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 execSync("gh auth token" (at position 6653)
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.
High11
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 fetchJson(url, options = {}) {
const response = await rateLimitedRequest(url, options);
if (" (at position 15800)
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.
highQ14Concurrent MCP Server Race ConditionMCP07-insecure-configT1068
Pattern "(?:read|write|modify|delete).*(?:file|path|directory)(?!.*(?:lock|mutex|semaphore|flock|atomic))" matched in source_code: "readFile" (at position 108)
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.
highC3Server-Side Request Forgery (SSRF)MCP04-data-exfiltrationAML.T0057
[AST taint] http_headers source "req.headers" (L3549) → assignment(L3549) → return_value(L3551) → ssrf sink "sessions.get(sessionId)" (L3838). HTTP GET with user-controlled URL. Module: http. Known sanitizers: validateUrl.
Validate URLs against an allowlist of permitted hosts. Use URL parsing to verify scheme and host before requesting.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L3338 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.
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 25623)
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: "open issues count, default branch, visibility, and language breakdown. Use as a starting point to understand a repository before exploring its content" (at position 26959)
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.
highN10Incomplete Handshake Denial of ServiceMCP07-insecure-configAML.T0054
Pattern "(?:createServer|listen)\s*\((?!.*(?:maxConnections|maxClients|connectionLimit|MAX_CONN))" matched in source_code: "createServer(" (at position 125292)
Enforce a handshake timeout (recommended: 30 seconds) — terminate connections that do not complete the initialize handshake within the deadline. Limit maximum concurrent pending connections. An attacker can exhaust server connection slots by initiating MCP connections without completing the handshake (Slowloris-style attack). Reference: MCP spec 2025-03-26 lifecycle — initialize MUST complete before functional requests.
highO6Server Fingerprinting via Error ResponsesMCP04-data-exfiltrationAML.T0057
Pattern "catch\s*\([^)]*\)\s*\{[^}]*(?:res\.(?:send|json)|return).*(?:err(?:or)?\.(?:message|stack|code)|connection|host|port|database)" matched in source_code: "catch (error) {
return toolError(error.message" (at position 118140)
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.
highC3Server-Side Request Forgery (SSRF)MCP04-data-exfiltrationAML.T0057
[AST taint] http_headers source "req.headers" (L3549) → assignment(L3549) → return_value(L3551) → ssrf sink "sessions.get(sessionId)" (L3700). HTTP GET with user-controlled URL. Module: http. Known sanitizers: validateUrl.
Validate URLs against an allowlist of permitted hosts. Use URL parsing to verify scheme and host before requesting.
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: "process.env.MCP_HTTP" (at position 3026)
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.
highN1JSON-RPC Batch Request AbuseMCP07-insecure-configAML.T0054
Pattern "Array\.isArray\(\s*(body|request|message|data|payload)\s*\)(?!.*(?:length\s*[<>]|maxBatch|batch[_\s-]?limit|MAX_BATCH))" matched in source_code: "Array.isArray(data)" (at position 20634)
Enforce a maximum batch size for JSON-RPC requests (recommended: 20-25 requests per batch). Reject batches exceeding the limit with a -32600 (Invalid Request) error. Implement per-batch timeout and memory limits. Reference: JSON-RPC 2.0 Section 6 (Batch) does not mandate limits — servers MUST enforce them.
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 13480)
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.
mediumC6Error LeakageMCP09-logging-monitoring
Pattern "catch\s*\([^)]*\)\s*\{[^}]*(?:throw|return).*(?:err|error)\.(?:message|stack)" matched in source_code: "catch (error) {
return toolError(error.message" (at position 118140)
Return generic error messages to clients. Log detailed errors server-side. Never expose stack traces, file paths, or internal error details in responses.
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.