paper-context-resolver

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime path is to read “paper link explicitly provided by the README” (and then fetch/ingest the paper record text such as arXiv/OpenReview/official pages), which is outsider-authored free text that can be injected into the LLM context via the paper content.