unifuncs-reader

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

• Third-party content exposure detected (high risk: 1.00). This skill calls the UniFuncs API to read arbitrary webpages, PDFs, and Word documents (see usage example python3 scripts/read.py "https://example.com"), so it ingests untrusted public third‑party content that the agent will read and interpret.