exa-search

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

• Third-party content exposure detected (high risk: 0.90). The skill's exa-ai search commands explicitly fetch and ingest content from the open web (web pages, news articles, research papers, code repositories and social platforms like LinkedIn) and includes options to summarize and parse that third-party content (e.g., --summary, --summary-schema), so the agent will read and interpret untrusted public/user-generated content.