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.mjsandsetup-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