semantic-scholar-api

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly directs the agent to fetch and consume public third-party data from OpenAlex (e.g., GET https://api.openalex.org/works) and CrossRef (e.g., GET https://api.crossref.org/works/{doi}), which the agent is expected to read and use to drive citation analysis and next actions, exposing it to untrusted external content.