update-pr

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md Step 1 and Step 2) runs gh pr view to fetch the PR title and body and explicitly instructs the agent to study and use that user-authored PR content to draft and apply updates, so untrusted, user-generated GitHub PR text could inject instructions that influence actions.