meitu-poster

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly documents configuring API credentials via commands that embed secret values (e.g., meitu config set-ak --value "..."), which encourages passing secrets as CLI arguments and would require the agent to handle secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The skill's Poster Analyse and Execute workflows explicitly ingest and parse user-provided/reference images (e.g., "Poster Analyse" reverse-engineer steps and CLI examples such as meitu image-generate --image "{ref_url}") — arbitrary external image URLs or user-supplied reference images are read and their extracted "visual DNA" directly influences prompt construction, routing, and generation decisions.