cloudflare-zerotrust

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Connects to casb.mcp.cloudflare.com, which is an official endpoint for Cloudflare's well-known services.
  • [DATA_EXFILTRATION]: No evidence of unauthorized data transmission. The skill utilizes environment variables (CLOUDFLARE_API_TOKEN, CLOUDFLARE_ACCOUNT_ID) for secure credential handling.
  • [PROMPT_INJECTION]: The skill processes external data (Cloudflare application names, policies, and security findings) which could theoretically contain malicious instructions. However, the tools are restricted to read-only operations, significantly limiting the impact of any potential indirect prompt injection.
  • Ingestion points: Data returned by list_access_applications, get_access_application, list_access_policies, get_access_policy, list_tunnels, get_tunnel, list_casb_findings, and get_casb_finding.
  • Boundary markers: None specified.
  • Capability inventory: Limited to information retrieval; no file-write, subprocess, or execution capabilities are present.
  • Sanitization: Standard handling by the MCP server and agent environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:29 PM
Security Audit — agent-trust-hub — cloudflare-zerotrust