BACH FileCommander
Filesystem, process management, sessions, search, OCR, ZIP, and PDF export tools.
0Tools
19Findings
0Stars
Mar 24, 2026Last Scanned
4 critical · 13 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
4critical
13high
1medium
1low
Critical4
criticalC1Command InjectionMCP03-command-injectionAML.T0054
Pattern "execSync\s*\(" matched in source_code: "execSync(" (at position 118026)
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.
criticalQ9Agentic Workflow DAG ManipulationMCP05-privilege-escalationAML.T0058
Pattern "(?:next[_\s]?(?:step|node|agent)|route[_\s]?to|redirect[_\s]?to|skip[_\s]?(?:step|node|validation))" matched in source_code: "redirect to" (at position 20624)
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).
criticalJ7OpenAPI Specification Field InjectionMCP03-command-injectionAML.T0054
Pattern "(?:summary|operationId|description).*\$\{|`.*(?:summary|operationId)" matched in source_code: "summary = `${t().fc_read_multiple_files.summary(successCount, errorCount)}\n${" (at position 52542)
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.
criticalQ13MCP Bridge Package Supply Chain AttackMCP10-supply-chainAML.T0054
Pattern "["']@modelcontextprotocol/sdk["']\s*:\s*["'](?:\^|~|\*|latest)" matched in source_code: ""@modelcontextprotocol/sdk": "^" (at position 147227)
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.
High13
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "fast-xml-parser@5.3.6" 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: "registerTool" (at position 11659)
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.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L1712 interpolates error variable "error" 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.
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 normalizePath(inputPath: string): string {
return path.normalize(" (at position 5742)
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.
highK4Missing Human Confirmation for Destructive OpsMCP06-excessive-permissionsAML.T0054
Pattern "(?:execute|run|perform|call).*(?:delete|remove|drop|truncate|destroy)(?!.*(?:confirm|approve|prompt|ask|verify))" matched in source_code: "running session and remove" (at position 74539)
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.
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 108639)
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.
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 { isError: true, content: [{ type: "text", text: t().common.errorGeneric(error instanceof Error ? error.message" (at position 79831)
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.
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 replacement
const newContent = content.replace(params.old_str, params.new_str);
await fs.writeFile" (at position 60039)
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).
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: "read_file.fileHeader(path.basename(filePath), formatFileSize(stats.size))}\n\n${content" (at position 13471)
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.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L2639 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.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L3189 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.
highQ14Concurrent MCP Server Race ConditionMCP07-insecure-configT1068
Pattern "(?:read|write|modify|delete).*(?:file|path|directory)(?!.*(?:lock|mutex|semaphore|flock|atomic))" matched in source_code: "readdir(dirPath, { withFile" (at position 3204)
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.
Medium1
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: "spawn(" (at position 48283)
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.