code-llm-papers-guide

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md "Paper Search" section contains a Python snippet that uses arxiv.Search to fetch and print arXiv papers (and the file also references public GitHub/arXiv links), so the skill explicitly ingests open third‑party content that the agent would read and that could influence downstream choices.