meta-repo

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to run meta git clone / meta git update (cloning arbitrary git URLs from .meta) and meta exec (running commands across child repos) and to install third‑party meta- packages, which means the agent will fetch and execute untrusted, user-generated repositories/plugins from public sources (e.g., GitHub) that can indirectly inject instructions affecting subsequent actions.