domain-authority-auditor

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to fetch and interpret third‑party web content and external tool data (see "Security boundary — WebFetch content is untrusted" and the "Automatically pull backlink profiles... AI citation data... knowledge graph" / veto-check sections), and those fetched pages and signals directly determine vetoes, caps, and next actions in the audit workflow.