github

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs using the gh CLI and gh api to fetch PRs, issues, workflow runs, and logs from GitHub (public, user-generated content), which the agent will read and use to drive actions/decisions, exposing it to untrusted third-party content that could carry indirect prompt injection.