cloudflare-redirector
Warn
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The
SKILL.mdfile contains instructions for the AI agent to persistently store sensitive Cloudflare API tokens in plain text by appending them to shell configuration files such as~/.zshrcand~/.bashrc. - [PROMPT_INJECTION]: The skill includes instructions in
SKILL.mdthat command the agent to override standard step-by-step execution and automatically perform a chain of sensitive operations—including credential verification, DNS modification, and code deployment—without further user confirmation. - [COMMAND_EXECUTION]: The skill makes extensive use of shell commands to manage environment variables, install project dependencies, and execute deployment tasks using the
wranglerCLI. - [EXTERNAL_DOWNLOADS]: The skill utilizes
pnpm dlxto dynamically download and execute the official Cloudflare Workers CLI (wrangler) from the NPM registry during the deployment process.
Audit Metadata