paper-summarizer

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts a PDF, URL, or arXiv ID (SKILL.md) and its summarize_paper implementation calls read_paper(source) in init.py to ingest text from those public third-party sources, so untrusted/user-submitted paper content could be read and materially influence the agent's outputs or decisions.