rhdh

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and processes public, user-generated GitHub content (PRs, comments, file contents) via the GitHub CLI (see references/github-reference.md and the CLI code that runs gh pr list, gh pr view, gh api repos/.../contents/... and uses PR data to decide actions like posting /publish), so untrusted third-party content is ingested and can influence tool actions and decision-making.