ingest-book

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

• Third-party content exposure detected (high risk: 0.80). The skill (readarr_ops.py) directly queries public Newznab indexers (e.g., NZBGeek/DrunkenSlug/Althub) via _query_newznab and the nzb_search/multi_search commands, ingesting and parsing untrusted external JSON/item data from those public APIs which are displayed and can influence subsequent tool actions, creating a pathway for indirect prompt injection.