configure-ecc

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

• Third-party content exposure detected (high risk: 0.80). Step 0 requires cloning the public GitHub repo https://github.com/affaan-m/everything-claude-code.git and the workflow then reads, copies, verifies, and optionally edits SKILL.md and other files from that cloned repository as part of its required installation/optimization steps, so untrusted third‑party content can materially influence agent actions and enable indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly runs a runtime git clone of https://github.com/affaan-m/everything-claude-code.git to fetch SKILL.md and skill directories which are then installed and used as agent instructions (i.e., remote content directly controls agent prompts and is a required dependency).