catalysis-hub-api

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to query the public GraphQL endpoint https://api.catalysis-hub.org/graphql (see "Core Queries" and the "Python Example") and to read/interpret returned reactions and publications as part of its workflow, so untrusted third‑party content from that open API could materially influence decisions or actions.