gh-stack

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

• Third-party content exposure detected (high risk: 0.75). This skill’s required runtime workflow relies on executing gh stack view --json, gh stack sync, gh stack submit --auto, and/or gh stack checkout <pr-number> which cause the GitHub CLI to fetch PR/stack metadata from GitHub (outsider-authored content) and pass it back to the agent via readable JSON/stdout.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill's prerequisite instructs installing the extension with "gh extension install github/gh-stack" (github/gh-stack), which fetches and installs remote executable extension code that the skill relies on at runtime.