astria-api

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

• Third-party content exposure detected (high risk: 0.80). This skill’s CLI explicitly fetches and ingests user-generated content from the Astria service and arbitrary remote URLs (e.g., astria prompts list, astria tunes list --gallery, astria cache refresh which snapshots prompts/tunes/packs, and --image-url/--input-image options and astria download), so the agent will read untrusted third-party content that can materially affect subsequent actions.