Langfuse Prompt Management
Manages prompts in Langfuse with version control, label management, and support for both text and chat prompt formats.
0Tools
6Findings
158Stars
—Downloads
Mar 22, 2026Last Scanned
Findings6
3critical
2high
0medium
1low
0informational
criticalC1Command InjectionMCP03-command-injectionAML.T0054
Pattern "`[^`]+`" matched in source_code: "`Prompt '${promptName}' is not a chat prompt`" (at position 2565)
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.
criticalC16Dynamic Code Evaluation with User InputMCP03-command-injectionAML.T0054
Pattern "compile\s*\([^)]*(?:req|input|param|args|body|user)" matched in source_code: "compile(args" (at position 2655)
Never pass user input to eval(), new Function(), exec(), or any code evaluation API. Use a proper expression parser (math.js, expr-eval, AST-based) if dynamic computation is required. If code execution is the feature (code sandbox), use a fully isolated container with no filesystem, network, or process access.
criticalQ13MCP Bridge Package Supply Chain AttackMCP10-supply-chainAML.T0054
Pattern "["']@modelcontextprotocol/sdk["']\s*:\s*["'](?:\^|~|\*|latest)" matched in source_code: ""@modelcontextprotocol/sdk": "^" (at position 6259)
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.
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "@modelcontextprotocol/sdk@1.5.0" has known CVEs:
Update dependencies to versions that patch known CVEs. Run 'npm audit fix' or 'pip-audit' to identify and resolve vulnerable dependencies.
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 329)
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.
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