configure-ecc

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly clones and ingests a public GitHub repository in Step 0 (git clone https://github.com/affaan-m/everything-claude-code.git) and then reads and acts on installed SKILL.md and rule .md files during verification and optional optimization, so untrusted third‑party content can influence the agent's actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly runs "git clone https://github.com/affaan-m/everything-claude-code.git" at runtime and then reads/copies SKILL.md files from that repo to supply skill instructions that directly control agent prompts and behavior, making the remote repo a required, runtime-controlling dependency.