meta-command-creator

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

• Third-party content exposure detected (high risk: 0.90). The skill's docs and templates (notably references/arguments-and-refs.md and references/templates.md) explicitly show using bash injection like !gh pr diff and !gh pr view --comments to inline GitHub pull-request diffs and comments (user-generated, public content) which the agent is instructed to read and summarize/act on, so untrusted third‑party content can directly influence agent behavior.