krt-jira-scribe

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 inspects Jira data from the external JIRA_HOST (see SKILL.md and references/jira-api.md: search/get issue/ transitions/boards/sprints/remote links), which is user-generated/untrusted content the agent reads and uses to decide creations, backlinks, and transitions, allowing indirect prompt-injection via Jira issue fields.