perplexity

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

• Third-party content exposure detected (high risk: 0.90). The skill integrates with Perplexity (via the Membrane connector) and instructs the agent to run "Search Perplexity" and add/search/consume search results that are gathered from across the open web (see SKILL.md "Search Query"/"Search Result" and the Perplexity overview), meaning the agent will ingest and act on untrusted third-party web content.