zotero-search

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly queries and ingests results from the public Semantic Scholar service (via pyzotero commands like s2search, related, citations/references) as documented in SKILL.md and references/semantic-scholar.md, and it uses those external JSON results to drive analysis, recommendations, and follow-up actions—exposing the agent to untrusted third‑party content that can influence behavior.