cubrid-pr-create

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests external issue content ("Step 3: If a JIRA ticket was identified, fetch context with /jira CBRD-XXXXX") and interacts with upstream GitHub remotes to read PRs/commits, meaning it reads untrusted, user-generated third-party content (JIRA/GitHub) and uses that content to draft PRs and influence actions.