Aphorisms

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflows explicitly fetch and ingest public web content (e.g., Workflows/FindAphorism.md Step 1 "If URL provided: WebFetch(url...)", Workflows/ResearchThinker.md and Workflows/AddAphorism.md which call WebSearch and cite external sources like Goodreads/WikiQuote/YouTube transcripts), and that untrusted user-provided or public content is read and used to drive recommendations, research, and edits—so third-party content can materially influence agent actions.