Security Verification Reports

Transparency is at the heart of our mission. See exactly how we evaluate every tool before recommending it.

Our 4-Phase Verification Methodology

Every tool in the ClineTools directory goes through a rigorous 4-phase audit. We don't just check boxes—we actively try to break things to ensure your safety.

1

Static Code Analysis

We manually review source code and run automated analysis looking for:

  • Obfuscated or minified code hiding functionality
  • Hardcoded URLs, especially to unknown domains
  • File system operations outside declared scope
  • Eval(), exec(), or dynamic code execution
  • Credential harvesting patterns
2

Sandbox Testing

Tools run in isolated environments where we monitor:

  • All file read/write operations
  • Network requests (DNS, HTTP, WebSocket)
  • Environment variable access
  • Process spawning and shell execution
  • Memory and CPU usage patterns
3

Attack Simulation

We actively attempt to exploit the tool:

  • Prompt injection via tool inputs
  • Path traversal to access sensitive files
  • Command injection through parameters
  • Data exfiltration via crafted responses
  • Privilege escalation attempts
4

Ongoing Monitoring

After approval, we continue watching:

  • Dependency updates and new CVEs
  • Maintainer changes and repository activity
  • Community-reported issues
  • Behavioral changes in new versions
  • Re-audit on every major version bump

Security Rating System

Each tool receives a letter grade based on our audit findings. Here's what each rating means:

Rating Meaning Criteria
A+ Excellent Passes all checks. Minimal attack surface. No network calls beyond declared purpose. Open source with active maintenance.
A Good Passes all critical checks. Minor findings that don't pose real risk. Well-maintained and transparent.
B Acceptable Passes critical checks but has areas for improvement. May have broad permissions or infrequent updates. Use with awareness.
C Caution Has notable security concerns. May lack transparency, have overly broad permissions, or show suspicious patterns. Listed with warnings.

Example Audit Reports

Below are sample security reports for tools in our directory. Full reports are available for Professional and Team subscribers.

Filesystem MCP Server

Audited: February 2026 · by Anthropic
A+

Official Anthropic MCP server for secure file system access. Provides read/write operations scoped to allowed directories.

PASS No command injection vectors
PASS Path traversal protected
PASS No network requests
PASS Scoped file access only
PASS No eval/exec usage
PASS Clean dependency tree
PASS Active maintenance
PASS Open source (MIT)

Puppeteer MCP Server

Audited: February 2026 · by Anthropic
A

Browser automation server enabling web scraping, testing, and interaction through Claude. Requires Chromium.

PASS No command injection vectors
PASS Sandboxed browser context
NOTE Makes network requests (by design)
PASS No credential harvesting
PASS No eval/exec usage
NOTE Large dependency tree (Chromium)
PASS Active maintenance
PASS Open source (Apache 2.0)

Brave Search MCP Server

Audited: February 2026 · by Anthropic
A

Web search integration using the Brave Search API. Enables Claude to search the web for current information.

PASS No command injection vectors
PASS No file system access
NOTE Network requests to Brave API only
PASS API key handled securely
PASS No eval/exec usage
PASS Minimal dependencies
PASS Active maintenance
PASS Open source (MIT)

Red Flags We Watch For

When evaluating AI tools, these are immediate warning signs that trigger deeper investigation or rejection:

  • Obfuscated source code — If we can't read it, we don't trust it
  • Unexplained network requests — Tools phoning home without clear purpose
  • Overly broad permissions — Requesting access far beyond stated functionality
  • Dynamic code execution — eval(), exec(), or loading remote code at runtime
  • No version pinning — Dependencies without locked versions can be silently compromised
  • Inactive maintenance — No updates for 6+ months with open security issues
  • Closed source with broad access — Can't verify what a tool does? That's a problem
  • Embedding hidden instructions — Prompt injection attempts in tool descriptions or responses

Have a tool you'd like us to audit?

Submit for Review