share-research-api

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

• Third-party content exposure detected (high risk: 0.90). This skill fetches and parses public, user-generated research metadata from the SHARE API (e.g., https://share.osf.io/api/v2/search/creativeworks/ as shown in SKILL.md and the Python usage example), so the agent directly ingests untrusted third‑party content that could influence its outputs or subsequent actions.