dev

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and processes GitHub PR review comments using gh api (see "Getting review comments" in SKILL.md, e.g., gh api repos/{owner}/{repo}/pulls/{pr}/comments), which are user-generated/untrusted content that the workflow reads and acts on (addressing comments and posting replies), thus allowing indirect prompt-injection.