000-jeremy-content-consistency-validator

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md and references/how-it-works.md explicitly require WebFetch for remote URLs and instruct the agent to discover and extract content from arbitrary public websites and GitHub repositories (e.g., "WebFetch permissions configured for remote URLs" and "Identify Website Sources" / "Identify GitHub Sources"), so it ingests untrusted third-party web content that can materially influence its discrepancy classifications and recommended actions.