hermes-api-client

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

• Third-party content exposure detected (high risk: 0.85). Hermes is instructed at runtime to “Navigate to {url}” / “Log into {site} … navigate …” and then returns scraped page text or extracted content into the agent’s LLM context via the Hermes API response, which can include outsider-authored free text from arbitrary URLs/pages.