cf-access-wall

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes Node.js scripts (gh-oauth-app.mjs and setup-access.mjs) to automate interactions with the Cloudflare API and GitHub settings dashboard.
  • [DATA_EXFILTRATION]: Securely handles credentials by reading and writing to an internal vault service (vaultGet, vaultSet). Sensitive data like GitHub client secrets and Cloudflare API tokens are handled in memory or stored in the vault, rather than being logged or displayed in the terminal.
  • [EXTERNAL_DOWNLOADS]: Communicates with official services including GitHub (github.com) for OAuth application creation and Cloudflare (api.cloudflare.com) for resource provisioning.
  • [PROMPT_INJECTION]: Processes declarative JSON specifications to drive infrastructure changes.
  • Ingestion points: External JSON spec files are ingested via command-line arguments in setup-access.mjs.
  • Boundary markers: The skill relies on standard JSON parsing; there are no specific markers to distinguish between data and embedded instructions.
  • Capability inventory: Possesses write access to Cloudflare's Zero Trust configuration, the ability to create GitHub OAuth apps via browser automation, and read/write access to the secret vault.
  • Sanitization: Values from the JSON specification (such as emails and domains) are used directly in API payloads without additional escaping or sanitization logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 05:05 PM
Security Audit — agent-trust-hub — cf-access-wall