perplexity-research

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly sends brain context to Perplexity which "searches + reads + synthesizes multiple pages with citations" (see Invocation and the curl call to https://api.perplexity.ai/chat/completions), meaning it ingests open/public web content that the agent will interpret and use to drive research outputs and recommended brain updates.