configure-ecc

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

• Third-party content exposure detected (high risk: 0.80). Yes — Step 0 explicitly instructs cloning the public GitHub repository (https://github.com/affaan-m/everything-claude-code.git) and later steps require the agent to read and act on installed SKILL.md and rule .md files (Steps 2, 4, 5), meaning the agent ingests untrusted public repository content that can influence installation/edits and thus 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 and relies on the fetched SKILL.md files and accompanying scripts/configs as required content that will be installed and used to drive agent behavior (and may include executable hooks), so the external repo directly controls prompts/instructions.