review-sparta

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

• Third-party content exposure detected (high risk: 0.70). The skill consumes content from external source URLs (see review_sparta_checks.py: check_qra_quality JOINs q.source_url to url_knowledge.uk.content and uses that content to compute verbatim grounding, CWE and other checks) as part of its required assessment workflow, so untrusted public web pages could materially influence scoring and subsequent actions.