architect-init

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

• Third-party content exposure detected (medium risk: 0.30). This skill’s required runtime workflow ingests free text from the user-provided $ARGUMENTS context and also reads and parses repository documentation/code files (e.g., scan_existing_docs() scans README.md, AGENTS.md, CONTRIBUTING.md, etc.), which are potentially attacker-authored within the user’s repo.