academic-writer

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

• Third-party content exposure detected (high risk: 0.90). The skill's core functionality (/paper search) and the Literature Search section in SKILL.md and rules/literature-search.md explicitly direct the agent to query and collect papers from public sites (Google Scholar, arXiv, DBLP, Semantic Scholar, ACM DL, IEEE Xplore), meaning it ingests open/public third‑party content into its workflow which can influence writing, citation, and subsequent tool actions and therefore could enable indirect prompt injection.