autoresearch

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

• Third-party content exposure detected (low risk: 0.10). The required workflow instructs the agent to search literature via external sources such as arXiv, CrossRef, Semantic Scholar, and Exa MCP (low risk since the agent selects search queries and fetches specific results), but does not monitor any unauthenticated inbound feeds or outsider submission channels.