workflow

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

• Third-party content exposure detected (high risk: 0.90). The article-evaluation-pipeline (references/article-evaluation-pipeline.md, Phase 1: FETCH) explicitly fetches arbitrary URLs using WebFetch or curl, saves and reads the retrieved article content (untrusted public web/user-generated content) as an input to deterministic validators and downstream analysis that determine verdicts and remediation actions, so third-party page content can materially influence agent decisions.