github-workflows

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow steps (e.g., "Before Making Changes" in SKILL.md and numerous commands in release-management.md) explicitly instruct inspecting external GitHub data via gh CLI (gh repo view, gh workflow list, gh run list, gh release list/view and viewing workflow files), which pulls untrusted, user-generated content from public repositories that the agent is expected to read and that can materially influence actions like creating releases or changing workflows.