ecosystem-health

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

• Third-party content exposure detected (high risk: 0.90). This skill mandatorily delegates to the docs-management skill to fetch live documentation and the changelog (explicitly citing the raw-githubusercontent-com-anthropics-claude-code-refs-heads-main-CHANGELOG) and also spawns the claude-code-guide for live web verification, meaning it ingests open/public third‑party docs/changelog content that the agent reads and uses to drive audits, categorizations, and tool actions.