literature-gap-finder

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

• Third-party content exposure detected (high risk: 0.90). This skill's Verification Process and Gap Verification Checklist explicitly direct the agent to search and use open/public sources (e.g., "Search major databases" and checklist entries naming Google Scholar, arXiv, CRAN, GitHub and authors' websites), so the agent is expected to fetch and interpret untrusted third‑party content that can influence its decisions.