zeabur-template

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly directs the agent to fetch external docs and raw templates from public URLs (e.g., https://raw.githubusercontent.com/zeabur/zeabur-template-doc/main/ and schema.zeabur.app, and commands like npx zeabur@latest template search / template get --raw and searching Docker Hub/GHCR) so the agent will ingest and act on untrusted, user-generated third‑party content as part of its workflow.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly tells the agent to fetch runtime documentation (including a "prompt.md") from https://raw.githubusercontent.com/zeabur/zeabur-template-doc/main/, which is a remote resource that would be fetched at runtime and could directly inject or control prompt/instruction content.