configure-ecc

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

• Third-party content exposure detected (high risk: 0.90). The skill's required Step 0 clones a public GitHub repository (https://github.com/affaan-m/everything-claude-code.git) into /tmp and subsequent Steps 2–5 explicitly read, grep, and edit installed SKILL.md and rule files from that clone, so untrusted third‑party content can directly influence installation decisions and edits.

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 files (and mentioned hooks/scripts) that are then installed and can directly control agent prompts or include executable hooks, so this is a required runtime external dependency.