cloudflare-mcp-server
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No malicious code, obfuscation, or data exfiltration patterns were detected. The skill follows best practices for Cloudflare Worker and MCP development.
- [CREDENTIALS_UNSAFE] (SAFE): No hardcoded credentials were found. The code correctly utilizes environment variables and placeholders for sensitive configuration.
- [Indirect Prompt Injection] (SAFE): The GitHub integration template ingests external repository metadata, creating a surface for indirect prompt injection. However, since this is the primary purpose of the integration and the template includes input validation, the severity is lowered to SAFE. Evidence Chain: [Ingestion points: GitHub repository metadata in templates/mcp-oauth-proxy.ts]; [Boundary markers: Not implemented in output formatting]; [Capability inventory: Tools for repository management (list, get, create, delete)]; [Sanitization: Strict Zod schema validation for tool inputs].
- [EXTERNAL_DOWNLOADS] (SAFE): All dependencies (e.g., zod, octokit, modelcontextprotocol/sdk) are standard and appropriate for the skill's functionality.
Audit Metadata