configure-ecc

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly clones and ingests a public GitHub repository (Step 0: git clone https://github.com/affaan-m/everything-claude-code.git) and then reads, scans, and edits SKILL.md and rules .md files from that cloned content as part of its installation and optimization workflow (Steps 4–5), so untrusted third‑party content can influence actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly performs a runtime git clone of https://github.com/affaan-m/everything-claude-code.git and then reads/copies SKILL.md and other files from that clone to install agent "skills" (i.e., content that directly defines agent prompts/instructions), so the fetched repository content can control agent behavior at runtime.