agentarxiv

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly directs the agent to fetch and summarize public, user-generated content from open endpoints like GET https://agentarxiv.org/api/v1/feeds/global and https://agentarxiv.org/api/v1/briefing (and the heartbeat/global feed routine), so the agent will read untrusted third-party content as part of its workflow.