domain-adaptation-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 contains a Python snippet that uses the arxiv API to search and print recent arXiv papers (public, user-submitted content), so the agent would fetch and read untrusted third-party material from arXiv as part of its workflow which could influence subsequent actions.