cliproxyapi-cloudflare-stack

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill embeds literal example API keys and credential JSONs (e.g., "sk-...", "grok-...") and instructs creating and copying credential files, which means secret values would be placed in files/commands and could be echoed or exfiltrated—this requires careful handling and poses a substantive exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow includes a Cloudflare Worker (“email-receiver”) that receives emails via Cloudflare Email Routing and stores/query data in D1, meaning outsider-authored email bodies/content can reach the LLM-enabled system indirectly through that ingest pipeline.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's installation steps fetch and execute remote code (git clone https://github.com/xsser/cliproxyapi-cloudflare-stack.git then running its scripts, and wget https://github.com/cloudflare/cloudflared/releases/latest/download/cloudflared-linux-amd64.deb followed by dpkg -i), so these runtime URLs could directly deliver and execute code.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill instructs the user to run privileged commands and modify system service files (sudo dpkg install, copying/editing /etc/systemd/system, and running systemctl), which directly change the machine's state and require elevated privileges.