upgrade-pack-generator

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md step 9) and scripts/research_upgrade_pack.py explicitly queue and run web.run to fetch and confirm public upstream docs, API reference pages, release notes and other web sources listed in research-bundle.json, meaning the agent ingests open/public third‑party pages that directly influence research, qualification, and rendered decisions.